Spain |
- Title of the course: Master in Soft Computing and Intelligent Data Analysis
- Level: Master
- Institute and departament: European Centre for Soft Computing and Universtity of Oviedo
- Short description of topics: Soft computing, Fuzzy logic, Neural networks, Evolutionary computation, Meta-heuristics, Probabilistic reasoning, Intelligent data analysis, Hybrid systems, ...
- Lecturer or responsible person: Luis Magdalena
- Other people involved: More than forty lecturers including: P. Bonissone, C. Borgelt, J.L. Castro, O. Cordón, S. Crone, D. Dubois, B. Gabrys, M.A. Gil, F. Herrera, J. Kacprzyk, R. Kruse, M. Laguna, P. Larrañaga, R. López de Mántaras R. Martí, C. Moraga, A. Nürnberger, G. Pasi and E. Trillas
- Language: English
- Web page: www.softcomputing.es/master
- Starting year of the course in its present form: 2009
- Goals/contents of the course: The general objective of the Master program is to prepare students for highly qualified positions in a wide range of jobs in the public and the private sector,
and to provide students with the foundations required to pursue a PhD degree.
Its specific objective is to train researchers to make significant contributions to scientific knowledge in soft computing and intelligent data analysis environment.
- Duration and period: One year, full time
- Additional information: Visit the web http://www.softcomputing.es/master or e-mail your questions to master@softcomputing.es
|
- Title of the course: Algoritmos Bioinspirados
- Level: Graduate/Postgraduate
- Institute and departament: Universidad de Extremadura, Departamento de Tecnología de los Computadores y de las Comunicaciones
- Short description of topics: Evolutionary Algorithms, Ant Colony Optimization, Particle Swarm Optimization, Neural Networks.
- Lecturer or responsible person: Francisco Fernández de Vega
- Language: Spanish
- Starting year of the course in its present form: 2002
- Goals/contents of the course: Introduce the basic concepts of Biologically Inspired Metaheuristics.
- Duration and period: One semester
- Approximate number of students: 15 postgraduates / 5 undergrads
- Intended audience: IT students
- Type: Elective
|
- Title of the course: Evolutionary Algorithms
- Level: Postgraduate (master level)
- Institute and departament: University of Málaga, Dpt. Languages and Computing Sciences
- Short description of topics: Introduction to evolutionary algorithms, relation to other metaheuristics (ACO, PSO, DE, SA, SS, TS, VNS...), decentralized algorithms (distributed and cellular EAs), parallel EAs, hybrid and memetic EAs, multiobjective approaches, dynamic optimization, theory, applications (telecoms, bioinformatics, software engineering...)
- Lecturer or responsible person: Prof. Dr. Enrique Alba
- Other people involved: Dr. Carlos Cotta
- Language: Spanish
- Web page: http://mop.cv.uma.es/course/category.php?id=91
- Starting year of the course in its present form: Every year, starting in September
- Goals/contents of the course: Design, implemention and use of evolutionary algorithms (and others) to solve real world problems of high complexity, dimensionality, etc.
- Duration and period: One year, full time
- The course is part of: Master in Software Engineering and Artificial Intelligence
- Type: Elective
|
- Title of the course: Evolutionary Computation
- Level: final year undergraduate
- Institute and departament: University Complutense de Madrid. Facultad de Informática
- Short description of topics: Introduction to the fundamental principles and practices underlying the field of evolutionary computation. Application of evolutionary algorithms to various optimization problems
- Lecturer or responsible person: Carlos Cervigón
- Language: Spanish
- Web page: http://www.fdi.ucm.es/profesor/ccervigon/
- Text book or classnotes: Book, Slides and Virtual Carmpus
- Slides or others supporting material: http://www.fdi.ucm.es/profesor/ccervigon/PE/PE.html
- Duration and period: second semester
- Approximate number of students: 60
- Type: elective
|
- Title of the course: Fundamentals of Soft computing
- Level: postgraduate
- Institute and departament: Department of Electronics and Computer Science
- Short description of topics: Machine learning, Bayesian networks, Evidence Theory, Fuzzy sets, Fuzzy reasoning
- Lecturer or responsible person: Alberto J. Bugarín Diz
- Other people involved: Paulo Félix Lamas, Miguel Rodríguez González
- Language: Spanish
- Web page: http://www.usc.es/gl/centros/fisica/materia.jsp?materia=38913&ano=60&idioma=7
- Starting year of the course in its present form: 2004
- Goals/contents of the course: The course deals with the foundations of some paradigms that are relevant for the treatment of uncertainty in computing: classical approaches such as the probability theory and the evidence theory and soft computing approaches such as fuzzy sets and the possibility theory.
The main goal is to achieve a thorough understanding of the foundations of these paradigms, and also to experiment with their use and practical application in a number of problems, especially in the field of knowledge representation and machine learning.
- Text book or classnotes: http://www.usc.es/gl/centros/fisica/materia.jsp?materia=38913&ano=60&idioma=7
- Slides or others supporting material: http://www.usc.es/campusvirtual/
- Duration and period: 3ECTS; February-May
- Approximate number of students: 5
- Intended audience: Ph.D. students
- The course is part of: M.Sc. "research in information technologies"
- Type: elective
|
- Title of the course: Intelligent Control
- Level: Postgraduate
- Institute and departament: University of Huelva, Department of Electronic Engineering, Computer Systems, and Automatics
- Short description of topics: Introduction to intelligent control. Evolutionary computation, neural networks and fuzzy logic from the perspective of the intelligent control.
- Lecturer or responsible person: A. Javier Barragán
- Other people involved: J. Manuel Andújar
- Language: Spanish
- Web page: http://uhu.es/noticieros/master-icseii/
- Starting year of the course in its present form: 2007
- Approximate number of students: 20
- Intended audience: Master students
- The course is part of: Master in engineering control, industrial computer and electronic systems
|
- Title of the course: Interdisciplinary Master in Cognitive Systems and Interactive Media
- Level: Postgraduate / MSc
- Institute and departament: Universitat Pompeu Fabra (Barcelona)
Department of Information and Communication Technologies
- Short description of topics: The mission of CSIM is to train the future generation of researchers and professionals that will investigate, develop, engineer, deploy and analyse the cognitive systems and interactive media that will populate our future societies. CSIM will achieve this goal through a fundamental interdisciplinary approach that combines science, engineering, arts and humanities to instil a deep understanding of the design, construction, deployment and analysis of cognitive systems and interactive media combined with the practical skills to realize them.
- Lecturer or responsible person: Prof. Narcís Parés
- Other people involved: Academic Director: Prof. Paul Verschure
- Language: English
- Web page: http://csim.upf.edu/
- Starting year of the course in its present form: 2007
- Goals/contents of the course: The context of the program is found in the consideration that the 21st century will witness a next industrial and societal revolution by the development and deployment of CSIMs in our society. These systems can be realized as pragmatic and functional products such as mobile devices and services; educational and edutainment systems; information systems and media applications; assistive applications; culture creation, dissemination and promotion systems; interactive systems for leisure activities; artistic installations, etc. What these systems have in common is that they must perceive, make decisions and behave in the real-world in close collaboration and interaction with humans and/or other artefacts. The final instantiation of the resulting applications and machines may be: robots, interactive installations and applications, intelligent-emotive buildings, systems and services for ambient assisted living, informational environments, etc.
- Text book or classnotes: http://csim.upf.edu/?q=courses_type
- Duration and period: 1 academic year
- Approximate number of students: 40
- Intended audience: Being an interdisciplinary program it accepts students from a wide range of backgrounds, as long as they are willing to commit themselves to this interdisciplinarity.
|
- Title of the course: Knowledge Engineering
- Level: undergraduate
- Institute and departament: Department of Electronics and Computer Science
- Short description of topics: -Automatic learning: trees and decision rules.
-Knowledge representation and reasoning with uncertainty
- Study of practical cases of application
- Lecturer or responsible person: Alberto J. Bugarín Diz
- Language: Spanish; Galician
- Web page: http://www.usc.es/es/centros/etse/materia.jsp?materia=37228&ano=60
- Starting year of the course in its present form: 2009
- Goals/contents of the course: The aim of the subject is to present the student a number of problems for whose resolution is not feasible to apply an algorithm, or whose algorithmic solution turns out to be difficult. These problems often find an acceptable solution through the use of methods involving a representation of the knowledge that is available about the particular problem, or about how humans solve problems in general.
Usually this knowledge is endowed with uncertainty. Ways of representing this knowledge on a useful way, on how to automatically acquire the above mentioned knowledge, how to find the most suitable type of reasoning and how to describe processes of reasoning and problem solving are described.
- Text book or classnotes: http://www.usc.es/es/centros/etse/materia.jsp?materia=37228&ano=60
- Slides or others supporting material: http://www.usc.es/campusvirtual/
- Duration and period: 3ECTS; November-January
- Approximate number of students: 40
- Intended audience: CS students
- The course is part of: B.Eng. Computer Science
- Type: Compulsory
|
- Title of the course: Machine Learning and Neural Networks
- Level: graduate/postgraduate
- Institute and departament: U.P.M. /C.A.R.
- Short description of topics: 1. Intelligence and learning
* What is intelligence?
* What are intelligent machines?
* The learning relevance
* Building intelligent machines
* Objectives of the subject
* Applications
2. Feature processing
* Objectives of feature processing
* Quality criteria
* Feature selection
* Unsupervised linear processing
* Supervised linear processing
3. Classical classifiers
* Objective of classifiers
* Classifier types
* Supervised classifiers
* Unsupervised classifiers
4. Machine learning general methodology
* Objectives
* Supervised and not supervised learning
* Learning challenges
* Building machine learning models
* Errors and validation
5. Bio-inspiration
* Intelligence and the cortex
* Cortex structure
* Visual intelligence
* Visual cortex
* Cortex working conclusions
6. Supervised Neural Networks: Multilayer Perceptron
* Artificial Neural Networks
* Perceptron and the MLP structure
* The back-propagation learning algorithm
* MLP features and drawbacks
* The auto-encoder
7. Non supervised Neural Networks: Self-organizing Maps
* Objectives
* Learning algorithm
* Examples
* Applications
8. State of the art, research and challenges
- Lecturer or responsible person: Pascual Campoy
- Language: English
- Web page: http://ocw.upm.es/ciencia-de-la-computacion-e-inteligencia-artificial/machine-learning-and-neural-networks
- Goals/contents of the course: The main objective is that the student can apply the most important techniques for Machine Learning, both the “Classical Techniques” and those based on “Artificial Neural Networks”, to solve problems using actual data, some of them based on synthetic data, useful for getting familiar with the techniques, and some others based on data from real-word applications. The problems include both supervised learning problems, as well as unsupervised problems. The student is aimed to understand the features common to any kind of machine learning technique, and also to be able to understand the advantages and drawbacks of every technique in order to solve a particular problem. The classical techniques are studied as the reference techniques that used mathematical solutions and with which the new soft-computing techniques based on Neural Networks are to be compared with. The examples are solved using Matlab © and the specific toolbox of Statistics and Neural-Networks. A good motivation for using the techniques based in Neural Networks is given, by presenting the main features and the general methodology of such bio-inspired techniques, when compared to classical ones.
GENERAL OBJETIVES
* Ability to apply theoretical concepts and techniques included in the table of contents.
* Ability to solve practical problems with both synthetic data and real word data using Matlab ©.
* Ability to team working.
EVALUATION ACTIVITIES
* Classroom exercises.
* Two collaborative Homeworks.
* Individual exam.
- Slides or others supporting material: http://ocw.upm.es/ciencia-de-la-computacion-e-inteligencia-artificial/machine-learning-and-neural-networks/lecture-notes
- Duration and period: 1 semester
- Approximate number of students: 30
- Intended audience: REQUIRED PREVIOUS SUBJETCS
* General Algebra
* Differential equations
- The course is part of: Master in Automatics and Robotics
|
- Title of the course: Master in Soft Computing and Intelligent Systems
- Level: Master
- Institute and departament: Department of Computer Science and Artificial Intelligence of the University of Granada
- Short description of topics: Fuzzy Logic, Artificial Neural Networks, Evolutionary Computation and
Probabilistic Reasoning, amongst others. Furthermore, it covers the use
of these techniques in the context of key problems such as Data Mining,
Bioinformatics, the Semantic Web, Robotics and Intelligent Databases,
amongst others
- Other people involved: Lectures of the Department of Computer Science and Artificial Intelligence of the University of Granada, along with lecturers from the Universities of Jaen and Cordoba, and prestigious guests from universities throughout the world for the Seminar on New Trends in Soft Computing and Intelligent Systems included as a compulsory course of the master.
- Language: Spanish/English
- Web page: docto-si.ugr.es
- Starting year of the course in its present form: 2006
- Goals/contents of the course: The master in Soft Computing and Intelligent Systems provides advanced
training in the field of Intelligent Systems, this training is useful
for professional development of students and to provide students with
the foundations required to pursue a PhD degree.
- Text book or classnotes: https://docto-si.ugr.es/master/intranet/AuthApp/index.php
- Slides or others supporting material: https://docto-si.ugr.es/master/intranet/AuthApp/index.php
- Duration and period: One year, full time
- Approximate number of students: 35
- Intended audience: This Master is aimed specifically at students with a degree in Computing or Computer Engineering, Electronic, Telecommunications and Industrial Engineering, and those with degrees in Physics or Mathematics or other closely related subjects.
- Type: 2 compulsory subjects and the rest elective
- Additional information: Please visit the website of the graduate school of the University of
Granada for administrative matters http://escuelaposgrado.ugr.es/
|
- Title of the course: Neural Networks and Fuzzy Logic
- Level: Postgraduate
- Institute and departament: University of Huelva, Department of Electronic Engineering, Computer Systems, and Automatics
- Short description of topics: Introduction to neural networks, perceptrons and backpropagation learning algorithm. Introduction to fuzzy logic and fuzzy systems, fuzzy reasoning, fuzzy modeling and fuzzy control.
- Lecturer or responsible person: A. Javier Barragán
- Other people involved: J. Manuel Andújar, Omar Sánchez
- Language: Spain
- Web page: http://uhu.es/noticieros/master-icseii/
- Starting year of the course in its present form: 2007
- Approximate number of students: 20
- Intended audience: Master students
- The course is part of: Master in engineering control, industrial computer and electronic systems
|
- Title of the course: Soft Computing for Scientists
- Level: Postgraduate
- Institute and departament: University of Santiago de Compostela. Department of Electronics and Computer Science
- Short description of topics: Fuzzy logic; Neural computation; Evolutionary computation; Hybrid solutions
- Lecturer or responsible person: Manuel Mucientes
- Other people involved: Manuel Fernández-Delgado, Francisco Herrera
- Language: Spanish
- Web page: http://www.usc.es/gl/centros/fisica/materia.jsp?materia=38901&ano=60&idioma=7
- Starting year of the course in its present form: 2007
- Goals/contents of the course: In this course the student will acquire the basic skills to solve real problems using soft computing techniques. The student will use software tools to apply the theoretical contents of the course to solve classic problems.
- Slides or others supporting material: http://www.usc.es/campusvirtual/
- Duration and period: 3 ECTS; Sep-Jan
- Approximate number of students: 10
- Intended audience: Ph. D. students
- The course is part of: M.Sc. "research in information technologies"
- Type: Compulsory
|
Argentina |
- Title of the course: Redes Neuronales y sus aplicaciones en Ingeniería
- Level: graduate
- Institute and departament: Universidad Tecnológica Nacional - Facultad Regional Santa Fe. Departamento Sistemas
- Short description of topics: Historical perspective. Biological comparison. The perceptron and multilayer perceptron. The radial basis function networks. The self organizing map. Recurrent networks. Learning rules. Supervised and unsupervised learning. Applications.
- Lecturer or responsible person: Dra. Georgina Stegmayer
- Other people involved: Dra. Milagros Gutiérrez
- Language: Spanish
- Web page: http://www.frsf.utn.edu.ar/33-Ingenieria-en-Sistemas.html
- Starting year of the course in its present form: 2004
- Goals/contents of the course: * Formar competencias y habilidades en el campo de las Redes Neuronales.
* Presentar una válida herramienta de análisis y modelado de problemas prácticos en Ingeniería.
* Presentar y discutir los principales tipos de redes neuronales y sus correspondientes reglas de aprendizaje.
- Text book or classnotes: http://www.frsf.utn.edu.ar/matero/visitante/index.php?id_catedra=78&ver=7
- Slides or others supporting material: http://www.frsf.utn.edu.ar/matero/visitante/index.php?id_catedra=78&ver=4
- Duration and period: 4 months, august to november
- Approximate number of students: 10
- Intended audience: last year computer science students
- The course is part of: B.S. in Systems Engineer
- Type: elective
|
Australia |
- Title of the course: Data Mining
- Level: Postgraduate
- Institute and departament: CQUniversity, School of Information and Communication Technology
- Short description of topics: Classification, Regression, Association Rule Mining, Text Mining, Neural Networks, Decision Tree, Support Vector Machine, Apriori.
- Lecturer or responsible person: Shawkat Ali
- Other people involved: Ian Moore, Neville Richter, Ahmad Saeed, Glen Thorpe, SANTOSO WIBOWO, Saleh Wasimi
- Language: English
- Web page: http://sites.google.com/site/shawkat69/home
- Starting year of the course in its present form: 2005
- Goals/contents of the course: Data mining is the process of finding useful patterns in data, and this course examines the basics of data mining, model building and testing, and interpreting and validating results. Appropriate software is used by students to implement these ideas in practice. Students experience the theoretical and practical aspects of data mining.
- Text book or classnotes: http://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20bB&product_isbn_issn=9780170136761&discipline_number=3072
- Duration and period: 6 Months Course
- Approximate number of students: 300
- The course is part of: MIT
- Type: Elective
- Additional information: You welcome to visit:
http://sites.google.com/site/shawkat69/home
|
Austria |
- Title of the course: Natural Computation
- Level: Undergraduate
- Institute and departament: University of Salzburg
Department of Computer Sciences
- Short description of topics: Evolutionary Computation, Artificial Neural Networks
- Lecturer or responsible person: Helmut A. Mayer
- Language: German (English)
- Web page: http://www.cosy.sbg.ac.at/~helmut/Teaching/NaturalComputation/index.html
- Starting year of the course in its present form: 1997
- Slides or others supporting material: http://www.cosy.sbg.ac.at/~helmut/Teaching/NaturalComputation/vorlesung.html
- Duration and period: 4 months, spring term
- Approximate number of students: 15
- The course is part of: B.S. Computer Science
- Type: elective
- Additional information: The course is divided into a theoretical lecture and more practical project work, where groups of students work on a specific topic.
|
Belgium |
- Title of the course: Modelling of Fuzziness and Uncertainty
- Level: undergraduate
- Institute and departament: Department of Applied Mathematics and Computer Science; Ghent University
- Short description of topics: Auxiliary order structures (poset, lattice, Boolean algebra, Morgan algebra, Kleene
algebra), Zadeh´s fuzzy sets, alternative operations on fuzzy sets, triangular norms and conorms, flou set theory, L-flou set theory, L-fuzzy set theory, representation theorem of Negoita and Ralescu, cartesian product, typical membership functions, linguistic variables and linguistic hedges, calculus of level sets, Zadeh´s extension principle, bounded fuzzy sets in Rn, convex fuzzy sets in Rn, indices of fuzziness, calculus of fuzzy quantities
- Lecturer or responsible person: Martine De Cock
- Language: Flemish
- Goals/contents of the course: In the end students should be familiar with the basic concepts and techniques from
fuzzy set theory and related models of uncertainty, among them L-fuzzy set theory and
flou set theory. The students should be ready to start more advanced courses offered in
the master of computer science and the master of applied mathematics.
- Duration and period: 1st semester
- Approximate number of students: 40
- Intended audience: senior undergraduates in mathematics
- The course is part of: B.S. in Mathematics
|
Brazil |
- Title of the course: Business Intelligence Master
- Level: Graduate
- Institute and departament: Pontifícia Universidade Católica- Rio de Janeiro
- Short description of topics: Decision Support Systems, Business Intelligence, Neural Networks, Fuzzy Logic, Genetic Algorithms, Data Mining, Scheduling, Decision support for uncertainties, Human Reliability, Support Statistic Methods, Decision Support Intelligence System Project.
- Lecturer or responsible person: A.Cruz, C.Aranha, D.Szwarcman, J.Domech Moré, J.Lazo, K.Figueiredo, M.Dias, M.Pacheco, M.Vellasco, M.Barros, R.Tanscheit
- Language: Portuguese
- Web page: http://bimaster.ica.ele.puc-rio.br/Home/Index.rails
- Starting year of the course in its present form: Spring 2007
- Goals/contents of the course: To promote a sound training of skilled professionals, able to participate in activities of design, design, development, maintenance, management, administration and to promote the use of methods and intelligent systems for decision support in general.
- Text book or classnotes: http://bimaster.ica.ele.puc-rio.br/notes/index.rails?name=Notas%20de%20Aulas
- Slides or others supporting material: http://bimaster.ica.ele.puc-rio.br/summaries/index.rails?name=Ementas
- Duration and period: 12 months, plus 3 months to finish final paper
- Approximate number of students: 40
- Intended audience: Students interested in learning new techniques, decision support systems DSS), and applying calculations to real-life problems
- The course is part of: graduate course (specialization)
- Additional information: http://bimaster.ica.ele.puc-rio.br/Home/Index.rails or e-mail your questions to bi-master.contato@ele.puc-rio.br
|
- Title of the course: Data Mining
- Level: postgraduate
- Institute and departament: UFPA-PPGEE
- Short description of topics: Initial considerations, objectives, characteristics and applications in the area of data mining. Artificial intelligence and knowledge discovery in database. Data analysis and preprocessing. Data mining tasks: classification, clustering, association and prediction. Basic principles and applications of classic data mining algorithms: decision trees and rules, association rules, neural networks, Bayesian networks, clustering, regression, etc. Analysis and interpretation of results. Preparation and presentation of projects.
- Lecturer or responsible person: Adamo Santana
- Language: Portuguese
- Starting year of the course in its present form: 2009
- Goals/contents of the course: Introduce the basic concepts of data mining, focusing on the main machine learning algorithms. Show the key tasks and techniques of data mining. Demonstrate the development of data mining in practical and real-world applications.
- Duration and period: One semester
- Approximate number of students: 30
- Intended audience: Postgraduate students
- The course is part of: No
- Type: Elective
|
- Title of the course: Design of Innovation with Genetic Algorithms
- Level: graduate
- Institute and departament: Institute of Mathematical and Computer Sciences
- Short description of topics: Properties for the success of competent genetic algorithms. Selectorecombinative genetic algorithms and facetwise models for theoretical analysis. Deduction of theoretical models for: population size, building blocks growing; convergence time, drift time, probabilistic choice of building blocks, control maps and mixing/innovation boundary. Principles of “linkage learning”.
- Lecturer or responsible person: Alexandre Claudio Botazzo Delbem
- Language: Portuguese
- Starting year of the course in its present form: 2009
- Duration and period: 24 hours, from October to November
- Approximate number of students: 15
- Intended audience: graduate students interested in theoretical aspects of Evolutionary Computation
|
- Title of the course: Estimation of Distribution Algorithms
- Level: graduate
- Institute and departament: Institute of Mathematical and Computer Sciences
- Short description of topics: Methods of Probabilistic Model Construction. Extended Compact Genetic Algorithm. Bayesian Optimization Algorithm, hierarchical Bayesian Optimization Algorithm, Search-space Reduction Algorithms.
- Lecturer or responsible person: Alexandre Claudio Botazzo Delbem
- Language: Portuguese
- Starting year of the course in its present form: 2008
- Duration and period: 24 hours, from August to September
- Approximate number of students: 15
- Intended audience: graduate students interested in Evolutionary Computation
|
- Title of the course: Evolutionary Computation
- Level: Graduate
- Institute and departament: Federal University of Pará - Electrical Engineering Graduate
- Short description of topics: Basics of genetic algorithms (encoding, operators, selection mechanisms, theoretical foundations, parallelism), and evolution strategies, evolutionary programming and genetic programming
- Lecturer or responsible person: Roberto Célio Limão de Oliveira
- Other people involved: Otávio Noura Teixeira
- Language: Portuguese
- Starting year of the course in its present form: 2002
- Duration and period: 1 semester
- Approximate number of students: 25
- Intended audience: Undergraduates students in engineering and computer science
- The course is part of: MS in Computer Science and MS/PhD in Electrical Engineering
- Type: compulsory
|
- Title of the course: Evolutionary Computation
- Level: postgraduate
- Institute and departament: University of Pernambuco / School of Engineering
- Short description of topics: Theoretical overview of main techniques and several practical hands-on projects
- Lecturer or responsible person: Prof. Fernando Buarque
- Other people involved: Prof. Carmelo Bastos
- Language: Portuguese
- Web page: in construction
- Starting year of the course in its present form: second semester
- Goals/contents of the course: -Further theoretical understanding of techniques;
-Development of CI practical skills (towards real-world applications);
-Increase awareness of CI potentials in solving complex problems.
- Text book or classnotes: Classnotes are being compiled into a book
- Slides or others supporting material: Being revamped
- Duration and period: One semester
- Approximate number of students: 10 postgrads + 20 undergrads (invited)
- Intended audience: Masters students and above
- The course is part of: Yes it is (undergrads are invited)
- Type: Compulsory (postgrads)
- Additional information: Postgrad students are team leaders for undergrads, mainly during projects.
|
- Title of the course: Evolutionary Computation
- Level: Graduate
- Institute and departament: Pontifícia Universidade Católica- Rio de Janeiro, Department of Electric Engineering
- Short description of topics: Basic Concepts, Evolution and Natural Selection; Components of an AG; Population size; Methods of Reproduction, Selection, Mutation and Crossover; Traditional AG; Prisoners' Dilemma (Machine Learning); Mathematical Foundations of GAs; Schema Theory; Deceptive AG (Deceptive) and Epistasis; Problems of Combinatorial Optimization; Optimization of Planning; Introduction to Genetic Programming; Introduction to Evolutionary Hardware; Environments and Programming Techniques of GAs;
Parallelization of GAs; Applications.
- Lecturer or responsible person: Marco Aurélio Pacheco
- Language: Portuguese
- Duration and period: 1 semester (March- July or August- December)
- Approximate number of students: 5 to 40, depending on the year
- Intended audience: Students interested in computational intelligence courses and methods of decision support systems
- The course is part of: graduate course (specialization)
- Type: compulsory/elective
|
- Title of the course: Evolutionary Systems Applied to Robotics
- Level: undergraduate
- Institute and departament: Institute of Mathematical and Computer Sciences
- Short description of topics: Canonical evolutionary algorithms. System modeling (representations, mono- and multi-objective formulations). Case studies of evolutionary algorithms applied to robotic systems.
- Lecturer or responsible person: Alexandre Claudio Botazzo Delbem
- Other people involved: Eduardo do Valle Simoes
- Language: Portuguese
- Starting year of the course in its present form: 2009
- Duration and period: 32 hours (from August to November)
- Approximate number of students: 30
- Intended audience: undergraduate students interested in evolutionary computation or robotics
- The course is part of: Yes
- Type: elective
|
- Title of the course: Fuzzy Logic
- Level: Graduate
- Institute and departament: Pontifícia Universidade Católica- Rio de Janeiro, Department of Electric Engineering
- Short description of topics: Definitions: Basic Characteristics, Types of Uncertainty;
The Rubik's Cube; Fuzzy Sets; Properties and Characteristics of Fuzzy Sets; Formats Fuzzy Sets; Logical Operations on Fuzzy Sets; Settings t-norm and t-conorm; Hedges; Fuzzy Relations and Compositions; Traditional Logic: Modus ponens and Modus Tollens; Fuzzy Logic: Generalized modus ponens; Fuzzy Systems; Rule Base, Inference Modules, Fuzzificaion, Defuzzification;
Fuzzy control; Applications
- Lecturer or responsible person: Ricardo Tanscheit and Marley Maria
- Language: Portuguese
- Duration and period: 1 semester (March- July or August- December)
- Approximate number of students: 5 to 40, depending on the year
- Intended audience: Students interested in computational intelligence courses and methods of decision support systems
- The course is part of: M.A. in Electric Engineering
- Type: compulsory/elective
|
- Title of the course: Fuzzy Systems
- Level: graduate
- Institute and departament: Computing Department - Federal University of São Carlos
- Short description of topics: Fuzzy sets and fuzzy logic; Approximate Reasoning; Rule-based Computations; Fuzzy Systems Modeling; Clustering methods; Genetic Algoritms; Genetic Fuzzy Systems.
- Lecturer or responsible person: Heloisa de Arruda Camargo
- Language: protuguese
- Starting year of the course in its present form: 2002
- Goals/contents of the course: The goal of the course is to provide a theoretical background for graduate students both at masters or doctoral level in computational intelligence, as well as the necessary knowledge to those students that are willing to develop their research work specifically in one of the topics studied in the course.
- Slides or others supporting material: http://www2.dc.ufscar.br/~heloisa/SN2007/SN.htm
- Duration and period: one semester, from august to november
- Approximate number of students: 10 per year
- Intended audience: graduate students, masters or doctorate
- The course is part of: Graduate Program in Computer Science - Federal University of São Carlos
- Type: elective
|
- Title of the course: Inteligência Computacional
- Level: undergraduate
- Institute and departament: COPPE/UFRJ
- Short description of topics: Soft computing techniques applied to data modeling.
- Lecturer or responsible person: Alexandre Evsukoff
- Other people involved: Nelson F. F. Ebecken
- Language: Protuguese
- Web page: http://www.poli.ufrj.br/graduacao_cursos_engenharia_computacao_informacao.php
- Starting year of the course in its present form: 2008
- Goals/contents of the course: - Linear models for classification and regression
- Introduction to fuzzy logic and fuzzy systems
- Introduction to neural networks
- Introduction to support vector machiines
- Text book or classnotes: http://www.support-vector.ws/
- Duration and period: 15 weeks
- Approximate number of students: 30
- Intended audience: undergraduate
- The course is part of: B.S. in Computer Engineering
- Type: compulsory
|
- Title of the course: Introduction to Computational Intelligence
- Level: Undergraduate
- Institute and departament: Fluminense Federal University - Electrical Engineering Department
- Short description of topics: Intelligent Agents, Probabilistic Methods, Optimization, Genetic Algorithms, Learning Theory, Neural Networks
- Lecturer or responsible person: Prof. Vitor Hugo Ferreira, D.Sc.
- Language: Portuguese
- Starting year of the course in its present form: 2010
- Approximate number of students: 10
- The course is part of: Electrical Engineering
- Type: Elective
|
- Title of the course: Introduction to Evolutionary Systems
- Level: graduate
- Institute and departament: Institute of Mathematical and Computer Sciences
- Short description of topics: Fundamental aspects of algorithms based on population evolution: genetic algorithms, evolutionary strategies, genetic programming, micro genetic algorithm, simulated annealing, univariate model distribution algorithm, etc.
The main features of algorithms based on colony behavior: ant colony optimization, particle swarm optimization, artificial bee colony, honey-bee mating algorithm, shuffled frog leaping, fish school search, bacterial foraging optimization, etc.
- Lecturer or responsible person: Alexandre Claudio Botazzo Delbem
- Language: Portuguese
- Duration and period: 21 hours, from March to April
|
- Title of the course: Multi-Objective Optimization
- Level: Postgraduate
- Institute and departament: University of Pernambuco / School of Engineering
- Short description of topics: Theoretical overview of main techniques and several practical hands-on projects. The approaches considered in the course are based on Evolutionary Computation and Swarm Intelligence.
- Lecturer or responsible person: Carmelo J. A. Bastos Filho
- Other people involved: Fernando Buarque de Lima Neto
- Language: Portuguese
- Web page: in construction
- Starting year of the course in its present form: 2007
- Goals/contents of the course: -Further theoretical understanding of techniques; -Development of CI practical skills (towards real-world applications); -Increase awareness of CI potentials in solving complex problems.
- Duration and period: one semester
- Approximate number of students: 8
- Intended audience: Masters students and above
- The course is part of: MSc. in Computer Science
- Type: elective
|
- Title of the course: Neural Networks
- Level: Graduate
- Institute and departament: Pontifícia Universidade Católica- Rio de Janeiro, Department of Electric Engineering
- Short description of topics: Understanding of Design and Manufacture of Integrated Circuit (IC); Project Methodology; Basic Characteristics: Learning, Association, Generalization and Robustness; History; Structure of Artificial Neuron; Interconnect Structures; Types of Learning - Supervised and unsupervised; Learning algorithms: Perceptron, Delta Rull, Back Propagation, Hopfield Network, Bidirectional Associative Memories, Self-Organizing Networks, Probabilistic Networks and Networks of Radial Basis Function; Temporal Networks (TDNN); Applications.
- Lecturer or responsible person: Marley Vellasco
- Language: Portuguese
- Duration and period: 1 semester (March- July or August- December)
- Approximate number of students: 5 to 40, depending on the year
- Intended audience: Students interested in computational intelligence courses and methods of decision support systems
- The course is part of: M.A. in Electric Engineering
- Type: compulsory/elective
|
- Title of the course: Neural Networks II
- Level: Graduate
- Institute and departament: Pontifícia Universidade Católica- Rio de Janeiro, Department of Electric Engineering
- Short description of topics: Issues of Generalization; Boundaries of architecture and Relation to Data Available; Adjustment and Adaptation of Neural Networks; Significance of Variables; Interconnect Structures; Self Organizing Hybrid Model; Support Vector Machines;
Reinforcement Learning; Principal Component Analysis
- Language: Portuguese
- Duration and period: 1 semester (March- July or August- December)
- Approximate number of students: 5 to 40, depending on the year
- Intended audience: Students interested in computational intelligence courses and methods of decision support systems
- The course is part of: M.A. in Electric Engineering
- Type: compulsory/elective
|
- Title of the course: Pattern Classification
- Level: Graduate
- Institute and departament: Pontifícia Universidade Católica- Rio de Janeiro, Department of Electric Engineering
- Short description of topics: • Introduction: Motivation, Key Applications, Features and Feature Vectors, Supervised and unsupervised classification;
• Classifiers Based on Bayesian Decision Theory: Bayesian decision theory, discriminant functions and Surfaces makers, the Case of Normal Distribution;
• Supervised Methods: Learning Bayesian Classifier Bayes and Maximum Likelihood Estimation, Classification and Capacity Issues Dimensionality, Window Type Methods parzen Verses 'Nearest Neighbor', Multiple Discriminant Fisher's discriminant functions Generalised Perceptron Algorithm, Non-separable Behavior, and Pseudo Inverse Least Squares, Relation to Discriminant Fisher, Widrow-Hoff Process and Methods of Stochastic Approximation;
• Unsupervised Methods: Mixture Densities, Bayesian Learning Not Supervised, Similarity Measures, Iterative Methods for unsupervised classification, Kohonen and Hybrid Methods
- Language: Portuguese
- Duration and period: 1 semester (March- July or August- December)
- Approximate number of students: 5 to 40, depending on the year
- Intended audience: Students interested in computational intelligence courses and methods of decision support systems
- The course is part of: M.A. in Electric Engineering
- Type: compulsory/elective
|
- Title of the course: Swarm Intelligence
- Level: postgraduate
- Institute and departament: University of Pernambuco / School of Engineering
- Short description of topics: Theoretical overview of main techniques and several practical hands-on projects. Among others, we can cite the following techniques: Particle Swarm Optimization, Ant Colony Optimization, Fish School Search, Glowworm Swarm Optimization, Bacterial Foraging Optimization, Artificial Bee Colony Optimization.
- Lecturer or responsible person: Carmelo J. A. Bastos Filho
- Other people involved: Fernando Buarque de Lima Neto
- Language: Portuguese
- Web page: in construction
- Starting year of the course in its present form: 2007
- Goals/contents of the course: -Further theoretical understanding of techniques; -Development of CI practical skills (towards real-world applications); -Increase awareness of CI potentials in solving complex problems.
- Text book or classnotes: Classnotes are being compiled into a book.
- Duration and period: One semester
- Approximate number of students: 6
- Intended audience: Masters students and above
- The course is part of: MSc. in Computer Science
- Type: elective
|
- Title of the course: Vector Optimization
- Level: graduate
- Institute and departament: Universidade Federal de Minas Gerais
Dep. of Mathematics
- Short description of topics: Multiobjective optimization. Cones and partial ordering. Pareto-optimal solutions: analytical characterization. Scalarization methods. Preference indication and decision. Deterministic algorithms for vector optimization. Stochastic algorithms for vector optimization. Applications.
- Lecturer or responsible person: Ricardo H. C. Takahashi
- Language: Portuguese
- Starting year of the course in its present form: 1998
- Text book or classnotes: http://www.mat.ufmg.br/~taka
- Duration and period: 60 hours
- Approximate number of students: 5-30 students.
- Intended audience: Graduate students in Computer Science, Applied Mathematics and Electrical Engineering.
- The course is part of: MSc and PhD in Mathematics and Electrical Engineering
- Type: Elective
|
Chile |
- Title of the course: Sofcomputing and Applications Seminar
- Level: Undergraduate and graduate
- Institute and departament: Depto Electronica UTFSM
- Short description of topics: Introduction, modeling and optimization, decision trees, introduction to neural networks, introduction to genetic algorithms, introduction to softcomputing based optimization methods, introduction to fuzzy logic, introduction to ensemble methods (i.e. bagging and boosting), hypothesis evaluation methods, introduction to statistical methods
- Lecturer or responsible person: Tomas Arredondo
- Other people involved: Prof. Werner Creixell
- Language: Spanish
- Web page: http://profesores.elo.utfsm.cl/~tarredondo/cursos.html
- Starting year of the course in its present form: 2005
- Goals/contents of the course: This course is an introduction to Softcomputing and some areas of application for this technology. Starting with AI based techniques, this course imparts information on inexact computation, evolutionary computation, neural networks, ensemble methods, hypothesis evaluation, statistical based methods.
- Duration and period: four month semester
- Approximate number of students: 20
- Intended audience: graduate and undergraduate student
- The course is part of: BSEE, MSEE
- Type: Compulsory for MSEE with concentration in Computer Engineering
- Additional information: THis is a seminar style course in which students perform research on a chosen subject and do three presentations on this during the semester. At the end they must present their results in the format of a conference paper.
|
Colombia |
- Title of the course: Mineria De Datos
- Level: undegraduate/graduate
- Institute and departament: Universidad del Cauca Departamento de Sistemas
- Short description of topics: 1 INTRODUCCIÓN A LA MINERÍA DE DATOS
2 EL PROCESO KDD
3 TÉCNICAS DE MINERÍA DE DATOS
4 MINERÍA DE DATOS EN LA WEB – WEBMINING
5 ÁREAS DE INTERES EN INVESTIGACIÓN
- Lecturer or responsible person: Carlos Cobos
- Language: Español
- Web page: www.unicauca.edu.co/~ccobos
- Starting year of the course in its present form: 2008
- Goals/contents of the course: OBJETIVO GENERAL
Este curso da a los participantes la posibilidad de conocer, comprender las técnicas básicas de minería de datos y saber como se aplican en problemas concretos de extracción de conocimiento útil para el análisis y la toma de decisiones.
- Text book or classnotes: 2. Larose, Daniel T. Discovering Knowledge in Data: An Introduction to Data Mining. Hoboken, NJ, USA: John Wiley & Sons, Incorporated, 2005. E-Book
- Slides or others supporting material: pis.unicauca.edu.co/moodle/course/view.php?id=462
- Duration and period: 1 semestre
- Approximate number of students: 18 estudiantes por semestre
- Intended audience: Estudiantes de ingeniería de sistemas o de la Maestría en Computación
- The course is part of: Si
- Type: Electivo
|
Czech Republic |
- Title of the course: Application of Artificial Intelligence
- Level: graduate level
- Institute and departament: Tomas Bata University in Zlin
Faculty of Applied Informatics
Nad Stranemi 4511
760 05 Zlin
- Short description of topics: The course is aimed at gaining knowledge about fundamentals of artificial intelligence, softcomputing and mainly evolutionary computation. Students will acquire knowledge about principles of particular types of evolutionary algorithms, their principles, areas of applications and also theory of multi-criterial optimization and computational complexity.
- Lecturer or responsible person: Ivan Zelinka
- Other people involved: Zuzana Oplatkova
- Language: Czech, English classes for foreign students. e.g. under Erasmus programme
- Web page: portal.utb.cz
|
- Title of the course: Introduction to mathematical methods for artificial intelligence
- Level: Undergraduate
- Institute and departament: University of Ostrava, Institute for Research and Applications of Fuzzy Modeling
- Short description of topics: Main directions in AI. Soft Computing from
the AI perspective. Neural networks, fuzzy modeling, particle swarm
optimization.
- Lecturer or responsible person: Martin Stepnicka
- Language: Czech (English)
- Web page: http://irafm.osu.cz
- Intended audience: Bachelor/Master students of mathematics and informatics
|
- Title of the course: Methods of Artificial Intelligence
- Level: graduate level
- Institute and departament: Tomas Bata University in Zlin
Faculty of Applied Informatics
Nad Stranemi 4511
760 05 Zlin
- Short description of topics: The course is aimed at gaining knowledge about fundamentals of artificial intelligence, softcomputing and mainly neural networks. Students will acquire knowledge about principles of particular types of nets, their training algorithms and possibilities of applications as e.g. classification, prediction, approximation, pattern recognition etc.
- Lecturer or responsible person: Zuzana Oplatkova
- Language: Czech, English classes for foreign students. e.g. under Erasmus programme
- Web page: portal.utb.cz
|
Egypt |
- Title of the course: Computational Intelligence in Operations Research and Decision Support
- Level: undergraduate
- Institute and departament: Operations Research and Decision Support, Faculty of Computers and Information, Cairo University
- Short description of topics: This course will cover the three main components of the field of Computational Intelligence: namely Evolutionary, Fuzzy, and Neural Computation. An emphasis will be made on the application of Computational Intelligence (CI) techniques to optimization, prediction and modeling. Related heuristic techniques such as Ant Algorithms, Tabu search, Simulated Annealing may also be covered. The advantages and limitations as well as the guidelines for selecting the most efficient approach for various types of problems will be addressed. The implementation of CI techniques for various problems will be stressed throughout the course.
- Lecturer or responsible person: Mohammed El-Beltagy
- Language: English
- The course is part of: B.S. in Operations Reserach and Descision Support
|
Finland |
- Title of the course: Evolving Intelligent Systems
- Level: Postgraduate
- Institute and departament: Aalto University School of Science and Technology (former Helsinki University of Technology), Dpt. of Information and Computer Science.
- Short description of topics: Evolving intelligent systems with an emphasis on rule-based. Methodological aspects, evolving rule-based systems, evolving clustering, applications in different areas, including process industry, autonomous systems and signal processing.
- Lecturer or responsible person: Federico Montesino
- Language: English
- Web page: https://noppa.tkk.fi/ (not active yet)
- Starting year of the course in its present form: 2010
- Text book or classnotes: Evolving Intelligent Systems. Methodology and Applications, P. Angelov, D. Filev and N. Kasabov (Eds.). IEEE Press Series on Computational Intelligence. Wiley, 2010.
- Duration and period: Sept.-Dec. 2010
- Approximate number of students: 10
- Intended audience: Mainly MSc students at the department but open for other MSc programs and shared programs with University of Helsinki.
- The course is part of: Degree Programme of Computer Science and Engineering, MSc in Machine Learning and Data Mining, and others.
- Type: Elective, seminar course.
|
France |
- Title of the course: Computational Intelligence
- Level: Post graduate
- Institute and departament: INSA Lyon, MSIS Program
- Short description of topics: I. Intelligent Systems
What is computational intelligence?
II. Fuzzy Logic
Fuzzy sets, fuzzy reasoning using fuzzy if-then rules.
Fuzzy modeling
Designing a Fuzzy expert system
III. Neural Networks
Mathematical modeling of neurons, perceptrons and its limitations.
Backpropagation learning algorithm and its limitations.
Unsupervised neural networks, clustering algorithms.
Designing neural networks
IV. Evolutionary Computation
How Evolutionary Computation Works?
Evolutionary programming, evolution strategies, genetic programming.
Designing simple genetic algorithms for optimizing objective functions
Swarm Intelligence
V. Hybrid Intelligent Systems
Why hybrid systems?
Architecture of a neuro-fuzzy system.
Evolutionary neural networks, evolutionary fuzzy systems and some hybrid frameworks.
VI. Data Mining
Basic concepts of data mining and knowledge discovery.
CI techniques for data mining.
VII. Application Case Study
Nonlinear system modeling, pattern recognition, financial modeling, multi-criteria decision making, data mining, Internet modeling etc.
- Lecturer or responsible person: Ajith Abraham
- Other people involved: -
- Language: English
- Starting year of the course in its present form: 2008
- Goals/contents of the course: This advanced course on computational intelligence introduces all the core components of modern intelligent systems with a focus on designing hybrid systems. Students will have hands on experience with some of the tools like neural networks, fuzzy systems, swarm intelligence and evolutionary computation. Students will have the opportunity to perform some research on applying hybrid approaches for practical problem solving.
- Text book or classnotes: http://www.softcomputing.net/tutorial.html
- Duration and period: Lectures: 30 hours, Practicals: 20 hours
- Approximate number of students: 10
- Intended audience: Students of Master of Science in Information Systems
- The course is part of: MSIS
- Type: Elective
- Additional information: Style mode of teaching:
Lecture, outside readings, research.
Examination schedule:
Final Exam 40 %
Assignments 20%
Research report (conference paper standard) 40%
|
- Title of the course: STATISTICAL MACHINE LEARNING
- Level: Graduate
- Institute and departament: ESPCI ParisTech
Signal Processing and Machine Learning lab(SIGMA lab)
- Short description of topics: Principles of statistical machine learning
Classification, kernel methods
Linear and nonlinear regression
- Lecturer or responsible person: Gerard DREYFUS
- Language: French
- Web page: http://graduateschool.paristech.fr/cours.php?id=159449
- Goals/contents of the course: introduction to statistical machine learning and its applications
- Text book or classnotes: Apprentissage statistique, G. Dreyfus et al. (Eyrolles, 2008)
- Slides or others supporting material: http://www.espci.fr/enseignement/ressources.php?e=sta
- Duration and period: Lectures : 11 hrs ; training sessions : 8 hrs
- Approximate number of students: 45
- Intended audience: Students with basic background in statistics
- The course is part of: ESPCI curriculum
- Type: Compulsory for physicists, elective for chemical physics students
|
Germany |
- Title of the course: Computational Intelligence
- Level: graduate
- Institute and departament: Cologne University of Applied Sciences; Institute of Communications Engineering
- Short description of topics: #1: Classical optimization strategies: objective function; constraints; multidimensional, multimodal, multiobjective optimization; LP problems and the simplex algorithm; Pareto front and Pareto set. /-/
#2: Neural networks: biological archetype; neurons, net-, activation-, output-function; topologies of neural nets; training using the backpropagation-algorithm. /-/
#3: Fuzzy logic: fuzzy set, membership functions; fuzzification; fuzzy inference algorithms; defuzzification methods. /-/
#4: Evolutionary algorithms: fitness, genotype, phenotype; coding the genotype; selection procedures; recombination/crossover algorithms; mutation operators
- Lecturer or responsible person: Rainer Bartz
- Language: German (optionally English)
- Web page: www.nt-rt.fh-koeln.de
- Starting year of the course in its present form: 2009
- Text book or classnotes: see web page
- Slides or others supporting material: see web page
- Duration and period: one semester; spring term
- Approximate number of students: 20
- Intended audience: students enrolled in a Master program
- The course is part of: M.Sc. Information Engineering; M.Sc. Mechatronics
- Type: elective
|
- Title of the course: Computational Intelligence in Modeling, Prediction and Signal Processing
- Level: Graduate (Masters)
- Institute and departament: ITEM, Department of Electrical Engineering (FB1/NW1 building), University of Bremen
- Short description of topics: Computational Intelligence in modeling, prediction and signal processing is an independent one semester course which will give you a basic understanding of various intelligent technologies such as, fuzzy logic, artificial neural networks and evolutionary computations (Genetic Algorithms) and also hybrid intelligent system such as neural-fuzzy networks etc., which can be applied for system modeling, data prediction, and signal processing purposes.
- Lecturer or responsible person: Dr.-Ing. Ajoy K. Palit
- Other people involved: Ph.D student from Dr. Palit's Research Group
- Language: English
- Starting year of the course in its present form: Winter Semester (October -March) 2002/2003
- Goals/contents of the course: - Introduction to computational intelligence
- Principal constituents of comput. intelligence
- Fuzzy sets and properties
- Fuzzy relation
- Fuzzy logic systems (Mamdani, Sugeno, singleton, relational model)
- Fuzzy inference mechanism
- Generation of rule (Wang’s method)
- Clustering and LSE based rule generation
- Optimization problems
- Application of evolutionary computations
- Neuro implementation of fuzzy system
- Introduction to ANFIS / MIMO and MISO neuro-fuzzy networks
- Backpropagation, Marquardt training algorithm for neuro-fuzzy network
- Problems in automatic data driven rule generation
- Application in system modeling, time series prediction and signal processing
- Text book or classnotes: www.springer.com/computer/artificial/book/978-1-85233-948-7
- Duration and period: 2 Hrs. Lecture / 1 Hr. Lab Exercise ( 15 Lectures and 15 Lab exercises)
- Approximate number of students: 20
- Intended audience: M.Sc Students of Information & Automation Engineering (IAE), Communication & Info. Technology (CIT), System Engineering
- The course is part of: The course is part of M.Sc in IAE, CIT & System Engineering
- Type: Compulsory for IAE , Elective for others
|
- Title of the course: Computational Intelligende
- Level: undergraduate/graduate
- Institute and departament: Technische Universität München
Systemtheoretic Neuroscience
Institute for Automation and Autonomous Systems
- Short description of topics: Introduction to theory and application of neuronal networks, fuzzy control techniques, search- and exploration-based machine learning approaches for optimization, statistical learning methods, evolutionary and genetic algorithms for optimization, reinforcement learning, distributed agent-based learning.
Applications: Design of intelligent software modules for real-time control of engineered systems and sensory information processing.
- Lecturer or responsible person: Jorg Conradt
- Language: English
- Web page: http://www.lsr.ei.tum.de/teaching/courses/courses-in-winter/computational-intelligence/
|
- Title of the course: Computational Methods in Bionik I
- Level: undergraduate/graduate
- Institute and departament: Technische Universität Braunschweig;Institut für Luft- und RaumfahrtsystemeInstitut für Wissenschaftliches Rechnen
- Short description of topics: Introduction to simulation and optimisation methods, overview about conventional optimisation methods, biological basics of biological evolution, introduction of Evolutionary Algorithms (EA) and in-depth explanation of different types like Evolution Strategies (ES), Genetic Algorithsm (GA, others. Preferable applications in industry and research; examples.
Introduction to Simualted Annnealing (SA) and Particle Swarm Optimisation based on their natural model.
- Lecturer or responsible person: Prof. Dr.-Ing. habil. Joachim K. Axmann
- Other people involved: Oliver Pajonk
- Language: German or English
- Web page: www.wire.tu-bs.de/lehre/ws10/e_bionik.html
- Starting year of the course in its present form: Winter semesters since year 1999
- Goals/contents of the course: The lecture ‘Computational Methods in Bionics’ is intended for students from engineering and natural science as well as from computer science and other departments. It will give an overview about numerical optimization methods in general and a detailed description of methods copied from nature and transferred to optimization, information management, steering and control: methods based on the mutation-selection principle, simulated annealing, social group behaviour of swarms.
The lecture will give an introduction in the biological mechanisms and will explain a transfer to computational procedures. Several examples will demonstrate the applicability of the methods.
|
- Title of the course: Evolutionary Algorithms
- Level: undergraduate
- Institute and departament: Department of Knowledge and Language Processing
Faculty of Computer Science
University of Magdeburg
- Short description of topics: Evolutionary algorithms o
Evolutionäre Algorithmen orient oneself by the biologicial evolution. With the help of random mutations, fusions (emulating the sexual reproduction), and specific selection, one tries to optimize functions and solve (combinatorial) opitmization problems.
This lecture starts with a short introduction into biological fundamentals. It then continues with an overview of different kinds of evolutionary algorithms. Advantages and disadvantages of these algorithms are examined and explained with examples. Besides related approaches and metaheuristics (e.g. simulated annealing) are covered as well.
- Lecturer or responsible person: Prof. Dr. Rudolf Kruse
- Other people involved: Christian Moewes
- Language: German
- Web page: http://fuzzy.cs.uni-magdeburg.de/wiki/pmwiki.php?n=Lehre.ISE1011
- Goals/contents of the course: - application of appropriate modeling technologies to desing evolutionary algorithms
- application of methods for numeric optimization for problem solving
- evaluation and application of evolutionary programming to analyze complex systems
- skills to desing evolutionary algorithms
- Text book or classnotes: http://fuzzy.cs.uni-magdeburg.de/wiki/pmwiki.php?n=Lehre.EA2010?userlang=en#Literatur
- Slides or others supporting material: http://fuzzy.cs.uni-magdeburg.de/wiki/pmwiki.php?n=Lehre.EA2010?userlang=en#Vorlesung
- Duration and period: weekly 90 minutes lecture and exercise
- Approximate number of students: 50
- Intended audience: Computer Mathematics, Computational Visualistics, Data and Knowledge Engineering, Computer Science, Engineering Computer Science, Business Computer Science
- The course is part of: Bachelor in Computer Science
- Type: elective
|
- Title of the course: Fuzzy Systems
- Level: graduate
- Institute and departament: Department of Knowledge and Language Processing
Faculty of Computer Science
University of Magdeburg
- Short description of topics: Fuzzy set theory is an extension of the classical set theory that can model imprecise and vague expressions of natural language such as big, small, hot, cold, etc. Fuzzy logic allows to formalize rules that contain such expressions of natural language. These rules can be utilized to support decision processes. The lecture "Fuzzy Systems" offers an introduction to both fuzzy set theory and fuzzy logic. Moreover it deals with applications of control engineering, approximate inference and data analysis.
- Lecturer or responsible person: Prof. Dr. Rudolf Kruse
- Other people involved: Christian Moewes
- Language: English
- Web page: http://fuzzy.cs.uni-magdeburg.de/wiki/pmwiki.php?n=Lehre.FS1011
- Starting year of the course in its present form: 1984
- Goals/contents of the course: - application of adequate modeling approaches to desing fuzzy systems
- application of methods for fuzzy data analysis and fuzzy rule learning
- proficiency to develope fuzzy systems
- Text book or classnotes: http://fuzzy.cs.uni-magdeburg.de/wiki/pmwiki.php?n=Lehre.FS1011?userlang=en#references
- Slides or others supporting material: http://fuzzy.cs.uni-magdeburg.de/wiki/pmwiki.php?n=Lehre.FS1011?userlang=en#slides
- Duration and period: weekly 90 minutes lecture and exercise
- Approximate number of students: 15
- Intended audience: Computer Mathematics, Computational Visualistics, Data and Knowledge Engineering, Computer Science, Engineering Computer Science, Information Technology, Mathematics, Medical Systems, Physics, Sports and Technology, Statistics, Business Computer Science
- The course is part of: Master in Computer Science
- Type: elective
|
- Title of the course: Intelligent Systems
- Level: undergraduate
- Institute and departament: Department of Knowledge and Language Processing
Faculty of Computer Science
University of Magdeburg
- Short description of topics: The students shall acquire knowledge about problems of knowledge engineering, the most important technologies for knowledge representation, reasoning methods in different forms of representation, heuristic search methods, and planning algorithms.
- Lecturer or responsible person: Prof. Dr. Rudolf Kruse
- Other people involved: Christian Moewes and Georg Ruß
- Language: German
- Web page: http://fuzzy.cs.uni-magdeburg.de/wiki/pmwiki.php?n=Lehre.ISE1011
- Goals/contents of the course: - skills to model and design knowledge-intensive applications by choosing problem specific modeling technologies
- application of heuristic search methods and learning systems to handle huge data sets
- skills to develope and evaluate intelligent and decision support systems
- evaluation and application of model approaches to develop cognitive systems
- Text book or classnotes: http://fuzzy.cs.uni-magdeburg.de/wiki/pmwiki.php?n=Lehre.ISE1011?userlang=de#literatur
- Slides or others supporting material: http://fuzzy.cs.uni-magdeburg.de/wiki/pmwiki.php?n=Lehre.ISE1011?userlang=de#Allgemeines
- Duration and period: weekly 90 minutes lecture and exercise
- Approximate number of students: 120
- Intended audience: Computational Visualistics, Computer Science, Information Technology, Engineering Computer Science, Mathematics, Sports and Technology, Business Computer Science
- The course is part of: Bachelor in Computer Science
- Type: compulsory for some fields of studies
|
Greece |
- Title of the course: Artificial and Computational intelligence
- Level: Undergraduate
- Institute and departament: University of Piraeus, Department of Industrial Management & Technology
- Short description of topics: Natural, artificial and computational intelligence. Symbolic- and sub-symbolic-level of representation. Artificial neural networks, genetic algorithms, fuzzy inference systems and their applications to real-world problems.
- Lecturer or responsible person: Tatiana Tambouratzis
- Language: Greek/English
- Web page: http://www.tex.unipi.gr/undergraduate/notes/ai/main.htm
- Starting year of the course in its present form: 2009
- Goals/contents of the course: Natural intelligence as an inspiration for artificial and computational intelligence.
The limitations of directly mimicking natural intelligence:
scaling problems, the importance of the framework (environment, materials etc.) of
naturally intelligent action. The notion of computational complexity.
The symbolic- and sub-symbolic-levels of representation. Artificial neural networks,
genetic algorithms, fuzzy inference systems and their applications to real-world problems.
- Text book or classnotes: Tutor's notes
- Slides or others supporting material: http://www.tex.unipi.gr/undergraduate/notes/ai/main.htm
- Duration and period: One semester
- Approximate number of students: 10
- Intended audience: Fourth-year undergraduate students
- The course is part of: B.Sc. in Industrial Management & Technology
- Type: Elective
- Additional information: This course can be complemented by a fourth-year dissertation in the fields of artificial neural networks, genetic algorithms, fuzzy inference systems and their applications to real-world problems.
|
India |
- Title of the course: Artificial Intelligence and Soft Computing
- Level: graduate
- Institute and departament: Dept. of Electronics and Tele-communication Engineering, Jadavpur University, Calcutta
- Short description of topics: Reasoning,
Machine Learning,
Intelligent Search,
Planning,
Visual and Linguistic Perception,
Basis of Fuzzy Sets for Approximate Reasoning
Neural Nets in Machine Learning
Swarm and Evolutionary Optimization Techniques,
Case Study 1: Criminal Investigation
Case Study 2: Intelligent Robotics
- Lecturer or responsible person: Prof. AMIT KONAR
- Other people involved: Dr. ARUNA CHAKRABORTY
- Language: ENGLISH
- Starting year of the course in its present form: 1994
- Goals/contents of the course: The course is meant for M.Tech. students of any engineering discipline as a prerequiste for their research program for graduate level thesis/dissertation work.
- Text book or classnotes: Artificial Intelligence and Soft Computing, CRC Press, Boca Raton, Florida.
- Duration and period: One semester
- Approximate number of students: 120
- Intended audience: M.Tech students of EE, ETCE, CSE, Bio-medical Engg. and Instrumentation Engg.
- The course is part of: M.S. in Computer Science
- Type: Elective Core
|
- Title of the course: Bio-inspired Computing
- Level: Graduate
- Institute and departament: Visveswaraya Technological University, Bangalore
- Short description of topics: Biologically Inspired Computing comprises of different Methodologies that solve problems in a distinct way. It consists of Genetic Programming (GP), Genetic Algorithm (GA), Gene Expression Programming (GEP), Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO) and Neural Computing.
These nature inspired computational tools having the ability to solve complex problems with high efficiency and potentially have many advantages. Many of these techniques are being applied to solve problems in all branches of engineering. This Workshop is mainly devoted to the Research Scholars and Faculty Members who have some prior knowledge on the above technologies and who would want to use them in their research. The Workshop is designated to help the researchers in either investigate on improving the technologies or use these technologies to solve problems in their research domain. There will be theory session and hands on practical sessions. The source code of different computing techniques are made available to the participants and each one of them must be tried and experimented in the laboratory session. Each participants shall be given a terminal for conducting experiments. More focus will be given to practical sessions. The participants are expected to have some knowledge about Matlab and C++ Programming.
- Lecturer or responsible person: Prof.N.Sundararajan, Nanyang Technological University, Singapore
- Other people involved: Dr.Sundaram Suresh, Nanyang Technological University, Singapore
Prof.T.N.Nagabhushan, Special Officer, VTU e-Learning Centre, Mysore
Dr.S.K.Padma, Professor of IS&E, SJCE, Mysore
- Language: English
- Web page: http://research.vtu.ac.in/broucher.html
- Starting year of the course in its present form: 2010
|
- Title of the course: Certificate Course on Machine Intelligence and Soft Computing
- Level: Postgraduate
- Institute and departament: Center for Soft Computing Research, Indian Statistical Institute, Kolkata
- Short description of topics: Pattern recognition; Image processing; Fuzzy sets; Neural networks; Evolutionary computation; Project work on real life problems.
- Lecturer or responsible person: S. K. Pal
- Other people involved: A. Ghosh, D.P. Mandal, M.K. Kundu, C.A. Murthy, S. Mitra, B. Chanda, P. Maji, K. Ghosh
- Language: English
- Web page: http://www.isical.ac.in/~scc
- Starting year of the course in its present form: August 2007
- Goals/contents of the course: This is a value addition course for post graduate degree holders. The objective of the program is to train the students with the scientific knowledge in soft computing and machine learning paradigm. This may help the students for getting suitable job or accelerating research activities.
- Duration and period: 6-8 months.
- Approximate number of students: 20
- Additional information: Visit the website: http://www.isical.ac.in/~scc
or email qreries to: scc@isical.ac.in
|
- Title of the course: Computational Intelligence
- Level: graduate
- Institute and departament: Dept. of Electronics and Tele-communication Engineering, Jadavpur University, Calcutta
- Short description of topics: Fuzzy Sets and Logic,
Fuzzy Control,
Fuzzy Pattern Recognition,
Fuzzy Databases,
Supervised Neural Learning,
Unsupervised Learning,
Reinforcement Learning,
Competetive Learning,
Support Vector Machine Classifier,
Evolutionary Computing,
Genetic Algorithm,
Particle Swarm Optimization Algorithm,
Differential Evolutionary Algorithm,
Artificial Immune Systems,
Ant Colony Optimization,
Hybridization of Computational Intelligence Models/Algorithms,
- Lecturer or responsible person: Prof. AMIT KONAR
- Other people involved: Dr. ANANDA S. CHOWDHURY, Dr.ARUNA CHAKRABORTY, Dr. SWAGATAM DAS
- Language: English
- Starting year of the course in its present form: 2007
- Goals/contents of the course: The primary aim of this course is to employ Computational Intelligence models in engineering problem solving. Research initiative undertaken by students in this new discipline is also strengthened with the theoretical underpinnings offered in this course.
- Text book or classnotes: Computational Intelligence: Principles, Techniques and Applications, Springer, 2006.
- Duration and period: one semester
- Approximate number of students: 75
- Intended audience: EE, ECE, CSE, IT, Instrumentation Engg, students parsuing their M.S. degree
- The course is part of: M.S. in Computer Science
- Type: Elective
|
- Title of the course: Computational Intelligence & Soft Computing
- Level: Post Graduate
- Institute and departament: Department of Computer Sc & Engg, Department of Electronics & Communucations, Gandhi Institute of Engg & Technology, Gunupur (under Biju Patnaik University of Technology, Rourkela, Odisha
- Short description of topics: The Course is for the 1st semester MTech CSE & ECE students.
- Lecturer or responsible person: Dr. Sasanko Sekhar Gantayat
- Other people involved: Dr. Mrutyunjaya Panda, Mr. Bichitrananda Patra
- Language: English
- Web page: www.giet.edu
- Starting year of the course in its present form: Every year June/July Month
- Goals/contents of the course: To know the Soft Computing concepts on Fuzzy Systems, Neural Networks, Genetic Algorithms and their applications in real life. And useful for further Research works.
- Text book or classnotes: Soft Computing - Jang et all
- Duration and period: 6 months
- Approximate number of students: 36(18+18)
- Intended audience: students
- The course is part of: M Tech
- Type: elective for CSE and Core for ECE
|
- Title of the course: Soft Computing
- Level: Post Graduate
- Institute and departament: ABV-Indian Institute of Information Technology and Management Gwalior, India
- Short description of topics: Artificial Neural Network, Fuzzy Logic, Genetic Algorithm, Differential Evolution, Particle Swarm Optimization, Artificial Bee Colony Optimization Algorithm, Bacterial Foraging Optimization Algorithm, Ant Colony Optimization algorithm
- Lecturer or responsible person: Prof. Anupam Shukla, Dr. P K Singh, Dr. Jagdish Chand Bansal
- Language: English
- Web page: www.iiitm.ac.in
- Goals/contents of the course: The course is designed to introduce some most popular soft computing techniques to PG students.
- Duration and period: One semester
- Approximate number of students: 50
- The course is part of: M.Tech.
- Type: Elective
|
Irland |
- Title of the course: Natural Computing
- Level: undergraduate/postgraduate
- Institute and departament: School of Computer Science and Informatics, University College Dublin
- Short description of topics: The field of Natural Computing has advanced rapidly over the past decade. One offshoot of this progress has been the development of a large family of algorithms inspired by Nature, including Biological, Social and Physical systems. Broadly speaking, these algorithms draw metaphorical inspiration from diverse sources, including the operation of biological neurons, processes of evolution, models of social interaction amongst organisms, and natural immune systems, in order to develop tools for solving real-world problems. This module provides an introduction to a broad range of Natural Computing algorithms and illustrates how they can be applied to real-world problems using a series of case studies.
In addition to teaching the essentials of Natural Computing, the module provides experience in the planning, executing, writing up, and critical evaluation of research.
- Lecturer or responsible person: Michael O'Neill
- Language: English
- Web page: http://ncra.ucd.ie/COMP30290/
- Starting year of the course in its present form: 2006
- Goals/contents of the course: On completion of the module students should be able to:
* Outline the main Natural Computing algorithms
* Compare and Contrast the different Natural Computing methods
* Solve a problem using Natural Computing
* Design an experiment in Natural Computing
* Write and critically review an academic paper
- Text book or classnotes: http://www.springer.com/computer/theoretical+computer+science/book/978-3-540-26252-7 and http://www.springer.com/computer/ai/book/978-1-4020-7444-8 and http://www.springer.com/engineering/book/978-3-642-00313-4
- Duration and period: 1 Semester
- Approximate number of students: 30
- The course is part of: BSc Computer Science
- Type: Elective
|
- Title of the course: Natural Computing and Applications
- Level: Postgraduate
- Institute and departament: School of Computer Science and Informatics, University College Dublin
- Short description of topics: Offered on UCD's MSc Negotiated Learning Computer Science & Structured PhD Elective This module provides an introduction to a broad range of Natural Computing algorithms and illustrates how they can be applied to real-world..
.problems using a series of case studies. The module also provides experience in the planning, executing, writing up, and critical. evaluation of research. In addition, this 10 credit module focuses on the final step of Innovation where the research is brought to bear on real world problems, and examines Innovation opportunities.
- Lecturer or responsible person: Michael O'Neill
- Language: English
- Web page: http://ncra.ucd.ie/COMP41190/
- Starting year of the course in its present form: 2010
- Text book or classnotes: http://www.springer.com/3-540-26252-0 and http://www.springer.com/1-4020-7444-1 and http://www.springer.com/978-3-642-00313-4
- Duration and period: 1 Semester
- Approximate number of students: 30
- The course is part of: MSc Computer Science
- Type: Elective
|
Italy |
- Title of the course: Artificial and Computational Intelligence
- Level: Graduate course
- Institute and departament: Faculty of Sciences, University of Salerno
- Short description of topics: 64 h lessons
12 h laboratory
I - AI
1 Introduction
2 Intelligent Agents
3 Problem-solving
4 Knowledge Representation
II - Pattern Recognition and Machine Learning
1 Introduction to Pattern Recognition
2 PDF estimation
3 Mixturee Models, Clustering and EM
4 PCA
5 Linear Models for regression
6 Linear Models for classification
7 Feature Analysis
III Laboratory of machine learning models and data mining
- Lecturer or responsible person: Prof. Roberto Tagliaferri
- Language: Italian
- Starting year of the course in its present form: 2010
- Goals/contents of the course: The student will study the methodologies of Machine Learning, Statistical Pattern Recognition and Artificial Intelligence with the aim of solving complex problems in the areas of data mining and multidimensional data analysis, and more specifically referring to problems of linear classification and regression, clustering and feature analysis.
- Text book or classnotes: Stuart Russel, Peter Norvig: “Artificial Intelligence: a modern approach” (Volume 1). Pearson Education 2010. C.M. Bishop: “Pattern Recognition and Machine Learning”, Springer Science, New York, 2006
- Slides or others supporting material: R.O. Duda, P.H. Hart, D.G. Stork: “Pattern Classification”, Wiley-Interscience, II edition, New York, 2001 I. Guyon, S. Gunn, M. Nikravesh, L.A. Zadeh: “Feature Extraction: Foundations and Applications”, Springer, Berlin, 2007
- Duration and period: October 2010 - January 2011
- Approximate number of students: 65
- Intended audience: M.S. Students in Computer Science
- The course is part of: M.S. in Computer Science
- Type: Compulsory
|
- Title of the course: Curriculum in "Computational Intelligence"
- Level: undergraduate
- Institute and departament: University of Bari, Department of Informatics
- Short description of topics: Foundations of Computational Intelligence (Fuzzy Logic, Neural Networks, Genetic Algorithms); Advanced numerical techniques; Cognitive modelling, Image processing.
- Lecturer or responsible person: Anna M. Fanelli
- Other people involved: Corrado Mencar, Giovanna Castellano, Ciro Castiello, Nicoletta del Buono, Laura Caponetti
- Language: Italian
- Web page: http://informatica.uniba.it/laurea_magistrale/Intelligenza%20computazionale.pdf
- Starting year of the course in its present form: 2010
- Goals/contents of the course: The curriculum is aimed at forming specialists capable of analyzing, designing and developing complex systems with Computational Intelligence methodologies. In particular, the curriculum has the main objective of providing for theoretical, methodological and technological skills to design systems with human-like features, such as learning, reasoning and fault tolerance with imprecise and incomplete knowledge.
- Duration and period: 3 months, October-December
- Approximate number of students: 10
- Intended audience: Undergraduate students (last year), Ph.D. Students
- The course is part of: MS in Informatics
- Type: elective
|
- Title of the course: Evolutionary Algorithms for Security
- Level: undergraduate
- Institute and departament: University of Catania, IPPARI Research Center
- Short description of topics: - a brief description on Computer Security notions.
- a brief explanation on computational complexity theory; search spaces and optimization techniques;
- Genetic Algorithms and Genetic Programming; Artificial Immune Systems; Swarm Intelligence;
- presentation of some published work on Security based on nature-inspired methodologies.
- Lecturer or responsible person: Mario Pavone
- Language: italian language
- Starting year of the course in its present form: 3
- Approximate number of students: 20
- The course is part of: B.S. in Applied Computer Science
|
- Title of the course: Intelligent Systems
- Level: graduate (MS)
- Institute and departament: Universita' degli Studi di Milano, Department of Information Technology
- Short description of topics: The course presents methodologies and techniques to implement intelligent systems for processing information and knowledge, i.e., systems which behaves like the human brain by employing computational intelligence approaches. In particular, the following main approaches will be studied: neural networks, fuzzy systems, and evolutionary computing.
- Lecturer or responsible person: Prof. Vincenzo Piuri
- Language: Italian
- Web page: http://www.dti.unimi.it/piuri
- Starting year of the course in its present form: 2009
- Goals/contents of the course: • Neural networks: Definitions. Neurons: structures, perceptrons, RBF. Neural topologies: feed-forward, feedback, SOM. Learning: supervised, unsupervised. Performance. Optimization. Classification and clustering. Associative memories. Prediction. Function approximation. Applications.
• Fuzzy logic and systems: Fuzzy sets. Membership functions. Fuzzy rules. Defuzzification. Fuzzy reasoning. Fuzzy systems. Rough sets. Performance. Applications.
• Evolutionary computing: Genomic representation. Fitness functions. Selection. Genetic algorithms. Genetic programming. Evolutionary programming. Evolutionary strategies. Differential evolution. Swarm intelligence. Artificial immune systems.
• Hybrid systems
- Duration and period: semester, oct.-dec.
- Approximate number of students: 15
- Intended audience: MS students in computer science (curricula: information systems, industrial informatics, systems and network security)
- The course is part of: MS in Computer Science
- Type: compulsory
|
- Title of the course: Natural Computation
- Level: graduate
- Institute and departament: University of Catania, Department of Mathematics and Computer Science
- Short description of topics: - explanation on computational complexity theory, and some NP-complete problems;
- search spaces and optimization techniques
- Evolutionary Strategy; Genetic Algorithms; Genetic Programming; Artificial Immune Systems; Swarm Intelligence and Ant Colony Systems;
- a brief, and quickly explanation on Learning Classifier Systems and Membrane Computing
- Lecturer or responsible person: Mario Pavone
- Language: Italian
- The course is part of: B.S. in Computer Science
|
- Title of the course: Problems and approaches in computational chemistry
- Level: graduate
- Institute and departament: Politecnico di Milano, DEI
- Short description of topics: Computational chemistry is a well developed intersection of chemistry and computer science that employs the results of theoretical chemistry to compute the structures and properties of molecules. Present computational chemistry can accurately calculate the properties of molecules that contain no more than 10-40 electrons. Approximate methods are available for larger molecules.
The course will introduce the methods used in the basic areas of computational chemistry:
1. The prediction of the molecular structure of molecules
2. Storing and searching for data on chemical entities
3. Identifying correlation between chemical structures and properties
4. Computational approaches to design molecules that interact in specific ways with other molecules (eg drug design)
After a review of the area we will present the open challenges.
Challenges in size: work with big molecules (proteins, etc), work on large data sets, etc.
Challenges in the meaning: classification of the chemical space, classification of the mechanisms space, etc.
Challenges in the perspectives: from "in vivo" testing to "in silico" testing.
Challenges in the hybridization with new areas: how proteomics, genetics, neurosciences can build over computational chemistry.
The course will be organized with the cooperation of external experts and problem holders.
- Lecturer or responsible person: Giuseppina Gini
- Other people involved: Emilio Benfenati (Mario Negri Institute, Milan)
- Language: English
- Web page: http://home.dei.polimi.it/gini/CompChem/
- Starting year of the course in its present form: 2008
- Goals/contents of the course: The goal is to introduce the students to the topic and to review with them relevant publications in the computer science and AI areas.
- Text book or classnotes: http://home.dei.polimi.it/gini/CompChem/lezioni.htm
- Slides or others supporting material: http://home.dei.polimi.it/gini/CompChem/
- Duration and period: 20 hours
- Approximate number of students: 25
- Intended audience: PhD student in ICT
- The course is part of: Doctorate in Information Technology at Politecnico di Milano
- Type: elective
|
Lithuania |
- Title of the course: Fuzzy Engineering
- Level: postgraduate
- Institute and departament: Kaunas University of Technology; Department of Informatics
- Short description of topics: Introduction. Particularities of the course. Facts of history. Mode of studying.
2. Fuzzy set introduction. Fuzzy arithmetic.
3. Fuzzy logic and fuzzy relations.
4. Fuzzy control systems.
5. Functional organization of equivalence block.
6. Functional organization of a block for fuzzy signal producing.
7. Fuzzy control systems features.
8. Fuzzy control systems applications.
9. Fuzzy cognitive maps: theory; generalizations.
10. Applications of fuzzy cognitive maps: public and international relations, military applications.
11. Applications of fuzzy cognitive maps: economics and business.
12. Applications of fuzzy cognitive maps: signal processing and process control.
- Lecturer or responsible person: Prof. Raimundas Jasinevicius
- Other people involved: Doc. Vytautas Petrauskas;
Lect. Radvile Krusinskiene.
- Language: Lithuanian; English
- Web page: www.krc.ifko.ktu.lt
- Starting year of the course in its present form: 2004
- Goals/contents of the course: Fuzzy engineering concerns with analysis, modeling and synthesis in different systems based on the way the brain deals with inexact information. The subject encompasses the basic concept of set theory, fuzzy logic, fuzzy logic control systems and fuzzy cognitive maps concept and applications in industry, business, military, information technology and social and political science. Main target: to design and control systems and their computer-based models under uncertainity when the environment for systems functioning and its criteria are described using digital and verbal information related to human considerations.
- Text book or classnotes: www.ifko.ktu.lt/~raimund; www.krc.ifko.ktu.lt/~cost
- Slides or others supporting material: www.ifko.ktu.lt/~raimund
- Duration and period: 16 weeks
- Approximate number of students: 5-10
- Intended audience: People, deepening abilities: a) to analyze, simulate and synthesise fuzzy systems under the uncertainty when the environment and criteria of functioning are described more by qualitative rather than quantitative parameters related to informal human considerations; b)to use fuzzy mathematics for formalization of fuzzy considerations and situations in different fields of practical activity: industry,science, computerics and information technology, social, public and political life.
- The course is part of: M.S. in Computerics
- Type: Elective
|
- Title of the course: Intelligent Systems
- Level: master
- Institute and departament: Vilnius Gediminas Technical University
Faculty of Electronics
Department of Electronic Systems
- Short description of topics: Knowledge about intelligent systems, their composition and working principles based on artificial neural networks, evolutional algorithms or fuzzy logic, is acquired. Simulation with Matlab of intelligent systems or their parts, and application of intelligent systems to process and analysis of sounds, images or other signals of technical nature are mastered.
- Lecturer or responsible person: Assoc. prof. Artūras Serackis
- Language: Lithuanian
- Web page: www.serackis.ten.lt
- Starting year of the course in its present form: 2008
- Goals/contents of the course: The main aim is to learn in the group to design, analyze and perfect intelligent systems or their parts, be able to ground selected decisions and their causes.
- Text book or classnotes: http://e-stud.vgtu.lt/users/?p=47207.35665&id=1882
- Slides or others supporting material: http://e-stud.vgtu.lt/users/?p=51267.38243&id=1882
- Duration and period: Lectures - 48 h per semestre; Laboratory works - 16 h per semestre; Individual work - 136 h per semestre
- Approximate number of students: 20
|
- Title of the course: Neural Networks in Signal Processing
- Level: Postgraduate
- Institute and departament: Vilnius Gediminas Technical University,
Electronics Faculty
- Short description of topics: Knowledge about artificial neural networks, their structures, training algorithms and application possibilities is acquired. Multilayer Perceptrons, Radial Basis Function Networks, Support Vector Machines, various dynamic neural networks are studied. Understanding, selection and optimization of neural network structures are mastered. Simulation of neural networks with Matlab is learned.
- Lecturer or responsible person: Prof Dalius Navakauskas
- Language: Lithuanian, English
- Starting year of the course in its present form: 2002
- Goals/contents of the course: To learn to design, perfect and apply artificial neural networks for various types and different nature signal processing.
- Duration and period: One semester
- Approximate number of students: 15-30
- Intended audience: Master students
- The course is part of: Master in Electronics Engineering
- Type: Elective
- Additional information: Teaching methods (full-time studies): a) lectures - 48 h per semester; b) practical works - 16 h per semester; c) individual work - 56 h per semester.
|
Mexico |
- Title of the course: An Introduction to Evolutionary Computation
- Level: Graduate-level (masters)
- Institute and departament: Department of Computer Science, CINVESTAV-IPN
- Short description of topics: Basics of genetic algorithms (encoding, operators, selection mechanisms, theoretical foundations, parallelism), as well as some notions of evolution strategies, evolutionary programming and genetic programming
- Lecturer or responsible person: Carlos A. Coello Coello
- Language: Spanish
- Web page: http://delta.cs.cinvestav.mx/~ccoello/genetic.html
- Starting year of the course in its present form: 2001
- Goals/contents of the course: To acquire basic knowledge about evolutionary algorithms in general and genetic algorithms in particular (terminology, operators, theoretical foundations).
- Text book or classnotes: http://delta.cs.cinvestav.mx/~ccoello/genetic.html
- Slides or others supporting material: http://delta.cs.cinvestav.mx/~ccoello/genetic.html
- Duration and period: 14 weeks (4 hours a week). Taught in the term May-August of each year
- Approximate number of students: 10
- Intended audience: Graduate students in computer science or a related area
- The course is part of: MSc in Computer Science
- Type: Elective
- Additional information: This course has no prior course requirements, but students need to know C/C++ programming (under Linux) and should have some basic background in math and statistics.
|
- Title of the course: Fuzzy Logic and Neural Networks
- Level: Undergraduate
- Institute and departament: CETYS University
- Short description of topics: Basics of softcomputing (fuzzy logic and neural networks) applied to problems of control engineering, pattern recognition, time series prediction and other real problems of implementation.
- Lecturer or responsible person: Nohe R. Cazarez-Castro
- Other people involved: Selene L. Cardenas-Maciel
- Language: Spanish
- Web page: http://www.nohe.mx
- Starting year of the course in its present form: 2000
- Goals/contents of the course: Knowing the theory and applications of soft computing.
- Text book or classnotes: http://www.nohe.mx
- Slides or others supporting material: http://www.nohe.mx
- Duration and period: 16 weeks, 4 hours a week
- Approximate number of students: 10
- Intended audience: Undergraduate students of the Engineering Department
- The course is part of: BS Electronics Systems (optional for other fiels)
- Type: Compulsory for BS Electronics Systems and elective for other fields.
- Additional information: http://www.nohe.mx
|
- Title of the course: Recuperación de Información de la Web (Web Information Retrieval)
- Level: undergraduate Computer Science Engineer
- Institute and departament: Cuerpo Académico Ciencias de la Computación
Dependencia Area Ciencias de la Información
Universidad Autónoma del Carmen
C. 56 No. 4 Esq. Avenida Concordia Col. Benito Juárez C.P. 24180
Cd. del Carmen, Campeche, México
Tel. 01 (938)-3811018 Ext. 1007 Fax. 1328
- Short description of topics: 1) Introducción. Evolución histórica. Situación actual. (Introduction. History. Actual situation)
2) Recuperación de Información (Information Retrieval)
3) Sistemas Pregunta Respuesta (Question Answering System)
4) Extracción de Información (Information Extraction)
5) Web Semántica (Semantic Web)
- Lecturer or responsible person: Andrés Soto Villaverde
- Language: Spanish
- Web page: http://tech.groups.yahoo.com/group/Web_Information_Retrieval/?yguid=81321554
- Starting year of the course in its present form: 2010
- Goals/contents of the course: Conocer las estrategias de recuperación de información de la Web, así como el uso de herramientas, bases de documentos, ontologías, tesauros y diccionarios empleados en dicha temática.
The goal of the course is that, at the end of it, the students will know different strategies of Web Information Retrieval as well as different tools like Lemur and GATE, corpora like TREC, CLEF, etc, ontologies, thesaurus, dictionaries, etc. They will also develop some computer tools oriented toward IR
- Text book or classnotes: J.A. Olivas; "LAS TÉCNICAS DE SOFT-COMPUTING EN LA RECUPERACIÓN DE INFORMACIÓN"
- Duration and period: 1 semester: 16 weeks x 4 hours per week
- Approximate number of students: 15
- Intended audience: Computer Science undergraduate students
- The course is part of: The course is part of B.S: in Computer Science
- Type: elective
- Additional information: It is a general, introductory course to this subject, not a specialized one.
|
|
Netherlands |
- Title of the course: Computational Intelligence
- Level: Graduate
- Institute and departament: Erasmus School of Economics, Erasmus University Rotterdam.
- Short description of topics: This course gives an in-depth introduction to the computational approaches for intelligent systems design. The emphasis is on the background and application of soft computing techniques. In particular, (a selection of) the following topics are considered.
- Modelling with fuzzy systems.
- Feed-forward neural networks.
- Self-organizing maps.
- Derivative-free optimisation with evolutionary algorithms.
- Neuro-fuzzy systems.
- Intelligent agents.
The relevance of these techniques is demonstrated by examples of applications from finance, logistics, marketing and economic modelling. Students also gain hands-on experience with Matlab in applying these techniques.
- Lecturer or responsible person: Uzay Kaymak
- Language: English
- Starting year of the course in its present form: 2002
- Goals/contents of the course: At the end of this course the student is able to:
- Describe computational approaches to intelligence.
- List the reasons for using computational intelligence systems.
- Design computational intelligence systems by following a data-driven or an expert-driven approach.
- Implement a computational intelligence technique in a programming environment like Matlab.
- Apply intelligent systems for solving problems in the domain of economics and management science.
- Duration and period: September - October, 8 weeks
- Approximate number of students: 20
- Intended audience: Master students, junior post-graduate students.
- The course is part of: M.Sc. in Economics & Informatics, Computational Economics
- Type: Compulsory
|
New Zealand |
- Title of the course: Advanced Mechatronics
- Level: undergraduate/graduate
- Institute and departament: Victoria University of Wellington, School of Engineering and Computer Science
- Short description of topics: Application of Computational Intelligence techniques to real-world problems. Application issues, rather than theory, are described as part of an Advanced Mechatronics course. Problem domains ranging from data mining to cognitive robotics are discussed. Topics from modern heuristics to advanced Evolutionary Computation techniques are investigated. The Torcs autonomous racing car platform is used for the course assessment to implement computational intelligence techniques in a complex environment. this course is intended to show the capability of Soft Computing techniques to solve interesting and fun problems.
- Lecturer or responsible person: Dr Will Browne
- Other people involved: Prof Dale Carnegie
- Language: English
- Web page: http://ecs.victoria.ac.nz/
- Starting year of the course in its present form: 2006
- Goals/contents of the course: This course provides a guide to advanced techniques in the field of Mechatronics. Design and construction of computer based systems, including the interaction between hardware, software and communication components focuses on embedded systems. Practical examples are drawn from sensors, measurement instruments, robots and cell phones to demonstrate the nature of these interactions. Artificial Intelligence techniques are introduced as a practical method for addressing these complex interactions.
- Text book or classnotes: Artificial Intelligence, Rob Callan, Palgrave
- Slides or others supporting material: n/a on Blackboard so not externally accessible
- Duration and period: one trimester-12 weeks
- Approximate number of students: 12
- Intended audience: Fourth year undergraduate/Masters students
- The course is part of: BE and ME in Engineering and Computer Science,
- Type: Elective
|
Philippines |
- Title of the course: Computational Intelligence I
- Level: Graduate
- Institute and departament: University of the Philippines, Department of Computer Science
- Short description of topics: Basic Concepts, Genetic Algorithms, Evolutionary Strategies, Evolutionary Programming. Genetic Programming. Ant Colony Systems, Particle Swarm Optimization, Memetic Algorithms, Student Mini-Project
- Lecturer or responsible person: Pros Naval
- Language: English
- Starting year of the course in its present form: 2008
- Duration and period: 1 semester (48 hours)
- Approximate number of students: 15
- The course is part of: MS Computer Science, PhD Computer Science
- Type: Elective
|
Poland |
- Title of the course: Computational Intelligence
- Level: graduate
- Institute and departament: Nicolaus Copernicus University, Dept. of Informatics
- Short description of topics: Computational Intelligence (CI) overview, types of adaptive systems, learning and applications. (2 h)
Visualization and exploratory data analysis: few variables, parallel coordinates and other direct multivariate visualization algorithms, Principal Component Analysis (PCA), Self-Organized Mappings (SOM) and Multidimensional Scaling (MDS). (7 h)
Theory: overview of statistical approaches to learning, bias-variance decomposition, expectation maximization algorithm, model selection, evaluation of results, ROC curves. (4 h)
CI packages in action: WEKA/RapidMiner and GhostMiner, presentation of algorithms available in these packages (2 h, more during lab)
Statistical algorithms: discriminant analysis - linear (LDA), Fisher (FDA), regularized (RDA), probabilistic data modeling, SVM and kernel methods. (4 h)
Density estimation and rule induction, separability criteria. (4 h)
Similarity based methods, generation of prototypes, similarity functions. (2 h)
Improving CI models: boosting, stacking, ensemble learning, meta-learning, information theory for selection of features. (5 h)
- Lecturer or responsible person: Wlodzislaw Duch
- Language: English or Polish
- Web page: http://www.is.umk.pl/~duch/Wyklady/CI_plan.html
- Starting year of the course in its present form: 2003
- Goals/contents of the course: Intro to CI, understanding methods in large packages
- Text book or classnotes: http://www.is.umk.pl/~duch/Wyklady/CI_plan.html
- Slides or others supporting material: http://www.is.umk.pl/~duch/Wyklady/CI_plan.html
- Duration and period: 30 h lecturs + 30 h lab
- Approximate number of students: from 5 to 45, depending on the year
- Intended audience: CS and computational physics students
- The course is part of: MSc in computer sciences and in informatics
- Type: elective
- Additional information: Web page has now a header in Polish, but all material is in English.
This course was also taught at the School of Computer Engineering, Nanyang Technological University in Singapore, 2003-2007.
|
Portugal |
- Title of the course: Adaptive Business Intelligence (ABI)
- Level: postgraduate
- Institute and departament: University of Minho, Department of Information Systems
- Short description of topics: 1 - Introductory ABI concepts: data mining, prediction, optimization and adaptability.
2 - Modern Learning and Optimization methods for ABI: supervised learning (e.g. neural networks, support vector machine, learning classifier systems), clustering, inductive logic programming, heuristic search (e.g. hill-climbing, tabu-search, evolutionary computation).
3 - Data mining and Forecasting for ABI:
4 - Exploration of ABI tools.
- Lecturer or responsible person: Manuel Filipe Santos
- Other people involved: Paulo Cortez and Rui Camacho (from FEUP)
- Language: English
- Starting year of the course in its present form: 2008
- Duration and period: one semester
- The course is part of: PhD program in Computer Science/ MSc in Information Systems Engineering and Management
- Type: Elective
|
- Title of the course: Intelligent Decision and Control
- Level: graduate
- Institute and departament: TU Lisbon, IST, Dep. of Computer Science and Engineeirng
- Short description of topics: fuzzy logic, neural networks, bio-inspired meta-heuristics (EA, GA, ACO, PSO, etc.), nonlinear modeling, classification
- Lecturer or responsible person: João Miguel Sousa
- Language: English/Portuguese
- Web page: https://fenix.ist.utl.pt/disciplinas/cdi/2009-2010/1-semestre
|
- Title of the course: Intelligent Systems
- Level: graduate
- Institute and departament: TU Lisbon, IST, Dep. Mechanical Engineering
- Short description of topics: Fuzzy logic, fuzzy control, neural networks, nonlinear modeling, classification
- Lecturer or responsible person: João Miguel Sousa
- Language: English/Portuguese
- Web page: https://fenix.ist.utl.pt/disciplinas/sint/2009-2010/2-semestre
- Starting year of the course in its present form: 1987
|
Romania |
- Title of the course: Artificial Intelligence
- Level: undergraduate
- Institute and departament: Technical University "Gheorghe Asachi" of Iasi, Department of Computer Science and Engineering
- Short description of topics: Introduction to Artificial Intelligence, Search Strategies, Game Playing, Game Theory, Constraint Satisfaction Problems, Evolutionary Algorithms, Knowledge Representation Methods, Inference in Propositional and Predicative Logic, Planning Methods, Fuzzy Logic, Probabilistic Reasoning, Supervised Learning, Classification Techniques, Neural Networks, Unsupervised Learning, Reinforcement Learning, Elements of ALife
- Lecturer or responsible person: Florin Leon
- Language: Romanian
- Web page: http://eureka.cs.tuiasi.ro/~fleon
- Starting year of the course in its present form: 2008
- Goals/contents of the course: The objective of the course is to present an overview of the problems characteristic to artificial intelligence, including search, knowledge representation and planning, with special focus on soft computing techniques such as evolutionary algorithms, fuzzy logic and neural networks.
- Text book or classnotes: http://eureka.cs.tuiasi.ro/~fleon/curs_ia.htm
- Slides or others supporting material: http://eureka.cs.tuiasi.ro/~fleon/curs_ia.htm
- Duration and period: 14 weeks, from October to January
- Approximate number of students: 120
- Intended audience: Undergraduate students with the specializations of "Information Technology" and "Computer Engineering"
- The course is part of: BSc in Computer Science
- Type: compulsory
|
- Title of the course: Dynamic Systems and Stability in Automotive Control
- Level: graduate
- Institute and departament: “Politehnica” University of Timisoara, Department of Automation and Applied Informatics
- Short description of topics: Dynamics, Stability and Control Problems in Automotive Embedded Systems Including Motion Control. Introduction to Soft Computing. Structures of Fuzzy Control Systems and of Fuzzy Inference Systems. Typical and Special Fuzzy Controllers. Basics of Neural Networks, Architectures. Neuro-fuzzy Systems. Derivative-free Optimization in Intelligent Control Systems.
- Lecturer or responsible person: Radu-Emil Precup
- Language: English
- Web page: http://www.aut.upt.ro/~rprecup/
- Starting year of the course in its present form: 2006
- Goals/contents of the course: The course involves the following objectives: (1) the study of dynamical properties and stability of control systems in automotive applications, (2) gaining an understanding of the functional operation of a variety of techniques specific to intelligent systems and intelligent control systems, (3) the study of their control-theoretic foundations, (4) learning analytical approaches to study properties, (5) gaining experience on the computer-aided design of intelligent systems in automotive embedded systems, and (6) acquiring competence and knowledge on the development of hardware and software applications for automotive systems using updated IT methodologies. The aim is to gain a “hands-on” working knowledge of several of the main techniques in intelligent control systems and an introduction to some promising research directions in automotive embedded systems.
- Text book or classnotes: http://www.aut.upt.ro/~rprecup/lectures.html
- Slides or others supporting material: http://www.aut.upt.ro/~rprecup/lectures.html
- Duration and period: 1 semester (February to June)
- Approximate number of students: 30
- Intended audience: MSc students (1st year) in Automotive Embedded Software
- The course is part of: MSc Program in Automotive Embedded Software at the “Politehnica” University of Timisoara
- Type: compulsory
|
- Title of the course: Fuzzy Control Systems
- Level: undergraduate
- Institute and departament: “Politehnica” University of Timisoara, Department of Automation and Applied Informatics
- Short description of topics: Basics of Fuzzy Sets. Fuzzy Inference Systems. Structure sand Analysis of Fuzzy Controllers and of Fuzzy Inference Systems. Fuzzy Controllers. Elements of Fuzzy Control Systems Design. Applications and Case Studies of Fuzzy Control.
- Lecturer or responsible person: Radu-Emil Precup
- Other people involved: Claudia-Adina Dragos, Daniela Barbulescu, Mircea-Bogdan Radac
- Language: Romanian
- Web page: http://www.aut.upt.ro/~rprecup/
- Starting year of the course in its present form: 2000
- Goals/contents of the course: The goals of the course are to: provide knowledge on fuzzy sets and fuzzy logic, provide knowledge on the development methodologies of fuzzy control systems for several applications, provide experience on the use of computer-aided tools in the development of fuzzy control systems, and provide knowledge on the practical aspects of fuzzy control systems. The aim is to gain experience on the development, tuning and application of fuzzy inference systems and fuzzy controllers and on their implementation as well.
- Text book or classnotes: http://www.aut.upt.ro/~rprecup/lectures.html
- Slides or others supporting material: http://www.aut.upt.ro/~rprecup/lectures.html
- Duration and period: 1 semester (February to June)
- Approximate number of students: 60
- Intended audience: BSc students (4th year) in Systems Engineering
- The course is part of: BSc Program in Systems Engineering at the “Politehnica” University of Timisoara
- Type: elective
|
- Title of the course: Intelligent Control Systems
- Level: graduate
- Institute and departament: “Politehnica” University of Timisoara, Department of Automation and Applied Informatics
- Short description of topics: Elements of Soft Computing in Intelligent Control Systems. Fuzzy Sets and Fuzzy Processing of Information. Structures of Fuzzy Inference Systems. Elements of Neural Networks. Neuro-fuzzy Systems. Derivative-free Optimization in Intelligent Control Systems. Elements of Multi-agent Systems.
- Lecturer or responsible person: Radu-Emil Precup
- Language: Romanian
- Web page: http://www.aut.upt.ro/~rprecup/
- Starting year of the course in its present form: 2009
- Goals/contents of the course: The course aims the following goals: provide knowledge on the theoretical basics of intelligent control systems (ICSs), learn the main techniques concerning ICSs; learn the analytical and numerical approaches to the analysis and implementation of ICSs, gain experience on the computer-aided design of ICSs, acquire some applications of fuzzy logic, neural networks, derivative-free optimization techniques and multi-agent systems applied to learning, adaptation, identification and pattern recognition in the framework of embedded systems, motion control, mechatronics and informatics, acquiring research skills in ICSs.
- Text book or classnotes: http://www.aut.upt.ro/~rprecup/lectures.html
- Slides or others supporting material: http://www.aut.upt.ro/~rprecup/lectures.html
- Duration and period: 1 semester (February to June)
- Approximate number of students: 60
- Intended audience: MSc students (1st year) in Automatic Systems Engineering
- The course is part of: MSc Program in Automatic Systems Engineering at the “Politehnica” University of Timisoara
- Type: compulsory
|
Russian Federation |
- Title of the course: Computational cognition
- Level: undergraduate/graduate/postgraduate
- Institute and departament: Novosibirsk State University, Mathematical Department
- Short description of topics: Main definitions from the Measurement Theory - scales, numeric representations, existence, unicity and adequacy problems; extraction information from data; representation information in the first-order logic; rules discovery on data in the first-order logic that are laws, probabilistic laws and maximum specific laws. Problems of knowledge – statistical ambiguity, prediction from probabilistic rules; new definition of prediction, solution of statistical ambiguity and prediction problems; discovering of the subject domain theory; logic programming, logic programs for expert systems; knowledge extraction from expert; consistent knowledge base including domain theory and expert knowledge.
- Lecturer or responsible person: Evgenii Vityaev
- Language: Russian
- Web page: http://math.nsc.ru/AP/ScientificDiscovery/pages/lectures.html
- Starting year of the course in its present form: 2007
- Goals/contents of the course: Expert system of computational cognition.
Full and consistent knowledge extraction from the expert and data.
- Text book or classnotes: http://math.nsc.ru/AP/ScientificDiscovery/pages/BookCC.html
- Slides or others supporting material: http://math.nsc.ru/AP/ScientificDiscovery/pages/lectures.html
- Duration and period: semester, every year
- Approximate number of students: 80-90
- The course is part of: B.S. in Mathematics and Applied Mathematics
- Type: compulsory
|
Saudi Arabia |
- Title of the course: Evolutionary Computation
- Level: Graduate
- Institute and departament: KFUPM, Computer Engineering Department
- Short description of topics: Introduction to the fundamental principles and practices underlying the field of evolutionary computation. Application of evolutionary algorithms to various optimization problems in engineering. Hybridization of evolutionary computing techniques with other disciplines such as Fuzzy logic, Neural Networks etc. Design and Modeling of computer engineering problem solutions based on the principles of evolutionary algorithms.
- Lecturer or responsible person: Zubair Baig
- Language: English
- Web page: http://faculty.kfupm.edu.sa/coe/zbaig/coe589.htm
- Starting year of the course in its present form: 2010
- Duration and period: 1 semester
- Approximate number of students: 10
- The course is part of: MS in Computer Engineering/Science
- Type: Elective
|
Scotland |
- Title of the course: Adaptive Intelligent Systems
- Level: postgraduate masters
- Institute and departament: Robert Gordon University, School of Computing
- Short description of topics: Techniques: evolutionary algorithms (GA, ES, PSO, ACO, EDA), local search, constraint satisfaction and optimisation. Applications: function optimisation, artificial life, network analysis, optimal control, scheduling, evolutionary art and music. Concepts: exploration v exploitation, local and global optima, satisfaction and optimisation, premature convergence, plateauing , linkage-related theory. Practical: problem representations, selection, heuristic operators, parameter choices, evaluation and tuning of algorithms, toolkits
- Lecturer or responsible person: John McCall
- Language: English
- Duration and period: 13 weeks
- Approximate number of students: 20
- Intended audience: Advanced Masters
- The course is part of: MSc Computing: Information Engineering
- Type: Compulsory
|
Switzerland |
- Title of the course: Modelling, Simulation and Optimization (Advanced Technologies Supporting Business Areas)
- Level: graduate
- Institute and departament: Institute for Information Systems
- Short description of topics: This module deals with selected methods out of the research and application area of Computational Intelligence. Methods treated in the lectures and seminar projects are, for instance, evolutionary search and optimisation technologies, neural networks, sophisticated data mining technologies, artificial intelligence, and every kind of hybrid intelligent system.
Besides the basic foundations and a broader theory, these methods are applied to business issues or other application areas of interest for modelling, simulating and analysing problems, for evaluating and assessing data, as well as for obtaining viable alternatives and optimised solutions.
The potential impact of computational intelligence is investigated. Different cases are examined where computational intelligence can provide a substantial support, for instance in management science,operations research, logistics, finance and banking, and computer science.
On successful completion of this module, the students will have gained knowledge of the objectives, implementation and use of such methods of computational intelligence.
- Lecturer or responsible person: Rolf Dornberger
- Other people involved: Thomas Hanne
- Language: English
- Web page: http://www.en.fhnw.ch/business/iwi/institute-for-information-systems-where-it-and-business-meet?set_language=en
- Starting year of the course in its present form: 2009
- Goals/contents of the course: 1. Overview of optimization problems
Defining, assessing and solving optimization problems
Objectives, constraints, parameter sets
2. Application / business areas
Examples where computational intelligence is supporting business areas
Logistics (airline, railway, etc.), engineering, finance, economics, management
3. Overview of computational intelligence
Evolutionary computation (focus), artificial neural networks, fuzzy logic
4. Optimization methods and metaheuristics
Genetic algorithm, evolution strategy, simulated annealing, swarm intelligence, ant colony based optimization
Software platform for optimization and machine learning
Using and extending the software platform
Repetition of programming and software engineering: Syntax and usage of Java, object-oriented programming
- Slides or others supporting material: available on request
- Duration and period: 1 semester (15 weeks x 4h)
- Approximate number of students: 20
- Intended audience: Students in the master program in Business Information Systems
- The course is part of: MSc in Business Information Systems
- Type: elective
|
Taiwan |
- Title of the course: Fuzzy Set Theory and Applications
- Level: graduate
- Institute and departament: Industrial Engineering &Engineering Management, National Tsing Hua University
- Short description of topics: Introduction to the theories & logic of fuzzy sets with uncertainties in information and its uses in systems optimization and decision making.
- Lecturer or responsible person: Hsiao-Fan Wang
- Language: English
- Web page: softlab.ie.nthu.edu.tw
- Starting year of the course in its present form: Feb. 2010
- Goals/contents of the course: The main contents are:
1. Introduction and Review of Set Theory
2. Fuzzy Sets and Operations
3. Fuzzy Numbers and Arithmetic
4. Fuzzy Relations
5. Fuzzy Events and Fuzzy Regression
6. Fuzzy Measures
7. Fuzzy Linear Programming
8.*Fuzzy Decision Making
9. Fuzzy Clustering and Pattern Recognition
10Trend of softt Computing
- Slides or others supporting material: softlab.ie.nthu.edu.tw
- Duration and period: One semester
- Approximate number of students: 30
- Intended audience: Engineering and Management students
- The course is part of: master/phd in Industrial Engieering & Engineering Management
- Type: elective
- Additional information: a term project is required
|
Tunisia |
- Title of the course: Advanced Intelligent Control
- Level: Postgraduate
- Institute and departament: Faculty of sciences, University El Manar, Tunis and Engineering school of Gabes, University of Gabes, Tunis.
- Short description of topics: Introduction to intelligent control,
Artificial Neural Networks (ANN): ANN for logic functions, Multi Layer Perceptron, learning algorithm, retro propagation algorithm, Process identification and control based on ANN.
Fuzzy Logic (FL): introduction, supervision of processes based on FL.
- Lecturer or responsible person: Faouzi Bouani
- Other people involved: -
- Language: French
- Web page: -
- Starting year of the course in its present form: 2008
- Goals/contents of the course: The context of the program is the use of fuzzy logic and neural networks in control scheme. This course deals with the synthesis of controllers based on artificial neural networks, internal model control based on neural networks, predictive neural networks control, supervision of processes based on fuzzy logic.
- Text book or classnotes: -
- Slides or others supporting material: -
- Duration and period: 20 hours, Half academic year
- Approximate number of students: 40
- Intended audience: Master students
- The course is part of: Master in engineering control, industrial computer and electronic systems
- Type: compulsory
- Additional information: -
|
Turkey |
- Title of the course: Evolutionary Computing
- Level: Graduate
- Institute and departament: Istanbul Technical University, Informatics Institute, Computer Science Program
- Short description of topics: The basics of evolutionary algorithms are only briefly reviewed in this course. The rest of the course covers advanced and current research topics in evolutionary computing.
- Lecturer or responsible person: Dr. A. Sima Uyar
- Language: English
- Web page: http://web.itu.edu.tr/~etaner/courses/EvoComp/
- Starting year of the course in its present form: 2003
- Goals/contents of the course: Brief review of evolutionary computing approaches: genetic algorithms, genetic programming, evolutionary strategies, evolutionary programming, differential evolution, grammatical evolution, memetic algorithms; Mathematical foundations: schema theorem, building block hypothesis, encodings, fitness functions, fitness scaling, fitness landscape analysis, experimental design and analysis; Constraint handling; Multiobjective evolutionary algorithms; Parallelization; Hybridization; Fitness approximation, Maintaining diversity; Handling uncertainties and noise; Dynamic environments; Co-evolution; Interactive evolution.
- Text book or classnotes: http://web.itu.edu.tr/~etaner/courses/EvoComp/
- Slides or others supporting material: http://web.itu.edu.tr/~etaner/courses/EvoComp/
- Duration and period: 3 hours per week for 14 weeks
- Approximate number of students: 5
- Intended audience: Intended for students working towards a PhD degree in Computer Science or Computer Engineering.
- The course is part of: PhD in Computer Science and Computer Engineering
- Type: Elective
- Additional information: Students are expected to have completed an introductory level course on the topic before taking this course. Students are also expected to be able to program efficiently in a modern programming language.
|
- Title of the course: Nature-Inspired Computing
- Level: Graduate
- Institute and departament: Istanbul Technical University, Institute of Science and Technology, Computer Engineering Program
- Short description of topics: This course provides an introduction to nature-inspired heuristics and their applications to numerical and combinatorial search and optimization problems.
- Lecturer or responsible person: Dr. A. Sima Uyar
- Language: English
- Web page: http://web.itu.edu.tr/~etaner/courses/NIC/index.html
- Starting year of the course in its present form: 2006
- Goals/contents of the course: Introduction to nature-inspired computing; classical local search and optimization heuristics; Simulated annealing; Tabu search; Evolutionary algorithms: genetic algorithms, evolutionary strategies, genetic programming, evolutionary programming, grammatical evolution, differential evolution; Swarm intelligence: ant colony optimization, particle swarm optimization; Artificial immune systems; Hybrid systems; Applications.
- Text book or classnotes: http://web.itu.edu.tr/~etaner/courses/NIC/index.html
- Slides or others supporting material: http://web.itu.edu.tr/~etaner/courses/NIC/index.html
- Duration and period: 3 hours per week for 14 weeks
- Approximate number of students: 15
- Intended audience: Intended for students working towards an MSc degree in Computer Science or Computer Engineering or for those MSc or PhD students from other disciplines who wish to use nature-inspired techniques in their applications and research.
- The course is part of: MSc in Computer Engineering
- Type: Elective
- Additional information: Students should be able to program efficiently in a modern programming language.
|
United Kingdom |
- Title of the course: Fuzzy Systems and Networks
- Level: final year undergraduate
- Institute and departament: University of Portsmouth, School of Computing
- Short description of topics: Formal models of fuzzy systems and networks, basic and advanced operations in fuzzy networks, feedforward and feedback fuzzy networks, comparative evaluation of fuzzy systems and networks.
- Lecturer or responsible person: Alexander Gegov (course lecturer)
- Other people involved: Nedyalko Petrov (software developer)
- Language: English
- Web page: http://www.port.ac.uk/departments/academic/comp/staff/title,3828,en.html
- Starting year of the course in its present form: 2009
- Goals/contents of the course: To provide students with theoretical knowledge on fuzzy systems and networks as well as with practical experience by using the Matlab Fuzzy Logic and Fuzzy Network toolboxes.
- Text book or classnotes: http://www.springer.com/engineering/book/978-3-540-38883-8
- Slides or others supporting material: http://uws.port.ac.uk/unitwebsearch/displayUnitDetails.do?objectId=58685748
- Duration and period: one semester
- Approximate number of students: 10
- Intended audience: PhD students, researchers, academics.
- The course is part of: BSc in Computer Science
- Type: elective
|
- Title of the course: Games Programming Competition
- Level: Undergraduate / Taught Postgraduate
- Institute and departament: College of Engineering, Mathematics and Physical Sciences, University of Exeter
- Short description of topics: Extra-curricular programming course with a 3 hour workshop schedule across two semesters culminating in a programming competition for CI in games agents
- Lecturer or responsible person: Kent McClymont
- Other people involved: Maximillian Dupenois
- Language: English
- Web page: http://people.exeter.ac.uk/km314/index.php?id=cig
- Starting year of the course in its present form: 1
- Goals/contents of the course: To provide a competitive environment with desirable prizes (such as company visits to games companies) to motivate students to explore and develop core programming skills which complement the primary programming modules taught as part of the current degree courses.
- Slides or others supporting material: http://people.exeter.ac.uk/km314/toroidwars2010/
- Duration and period: 15 weeks
- Approximate number of students: 8
- Intended audience: Undergraduates
- The course is part of: No
- Type: Elective
|
- Title of the course: Genetic Programming and its Applications
- Level: unergraduate/graduate
- Institute and departament: University of Essex, School of Computer Science and Electronic Engineering
- Short description of topics: The aim of this module is to give an introduction to the main techniques and applications of genetic programming within the broader context of evolutionary computation.
- Lecturer or responsible person: Prof Riccardo Poli
- Language: English
|
- Title of the course: Intelligent Systems and Control
- Level: MSc, MEng
- Institute and departament: University of Glasgow, School of Engineering
- Short description of topics: An intelligent system utilises computational intelligence to analyse interconnections between causes, drivers and effects of the system so as to model and design, as well as control, their dynamic interactions in a holistic manner. Topics in the intelligent systems part of this course comprise machine learning and optimisation, artificial neural networks, fuzzy systems and control, genetic algorithms, and computer-automated design (CAutoD). The classical and modern control part includes in-depth anal¬ysis and design of proportional, integral and derivative (PID) control systems, linear and nonlinear systems and control in the state space.
- Lecturer or responsible person: Yun Li
- Language: English
- Web page: www.elec.gla.ac.uk/~yunli/ga_demo
- Starting year of the course in its present form: 1995 (as "Neural and Evolutionary Computing")
- Goals/contents of the course: To introduce students to computational intelligence, intelligent systems, advanced PID control, and design of control systems by machine learning and artificially evolution.
- Duration and period: 40 hours
- Approximate number of students: 30
- Intended audience: postgraduate or final year undergraduate
- The course is part of: MSc/MEng in E&EE
- Type: Elective
- Additional information: Syllabus:
In-depth analysis and design of proportional plus integral plus derivative (PID) control systems. Linear and nonlinear dynamic models in state space, linearization techniques and modern control. Optimisation of control systems to meet given performance specifications in terms of desired response, stability and robustness. Fuzzy logic, inference, decision making and fuzzy control. Artificial neural networks, learning algorithms and neuro-controllers. Genetic algorithms and evolutionary computation for machine learning, search, optimisation and adaptation. Interfacing with system simulators to transform Computer-Aided Design (CAD) to Computer-Automated Design (CAutoD).
|
- Title of the course: MSCI 522 Data Mining
- Level: Postgraduate
- Institute and departament: Lancaster University Management School, Dept. of Management Science
- Short description of topics: Teaching the algorithms of computational intelligence, with prarticular emphasis on neural networks, in the context of corporate data mining.
- Lecturer or responsible person: Dr. Sven F. Crone
- Language: English
- Web page: http://www.lums.lancs.ac.uk/masters/management-science/modules/multivariate-statistics-data-mining/
- Starting year of the course in its present form: 2005
- Duration and period: 20 lecture hours + labs
- Approximate number of students: 40
- Intended audience: Students at Master level
- The course is part of: MSc Management Science, Marketing Analytucs, Logistics & Supply Chain management, Quantitative Finance
- Type: compulsory / elective
|
United States |
- Title of the course: Adaptive Optimization
- Level: Graduate
- Institute and departament: Auburn University, Industrial and Systems Engineering
- Short description of topics: Introduction to meta-heuristics, simulated annealing, genetic algorithms, evolutionary strategies, tabu search, ant colony methods, particle swarm optimization, handling constraints, multi-objective optimization
- Lecturer or responsible person: Alice E. Smith
- Language: English
- Starting year of the course in its present form: varies
- Goals/contents of the course: Survey course of popular adaptive optimization methods.
- Duration and period: 1 semester, 3 credit hours
- Approximate number of students: 20
- Intended audience: Graduate students in engineering
- Type: Elective
- Additional information: Extensive programming requirement. Any language acceptable.
|
- Title of the course: Bio-Inspired Intelligent Systems
- Level: Undergraduate
- Institute and departament: Murray State University, Engineering and Physics
- Short description of topics: Genetic Algorithms, Particle Swarm Optimization, Neural Networks
- Lecturer or responsible person: James Hefeford
- Language: English
- Starting year of the course in its present form: 2006
- Approximate number of students: 10
- The course is part of: B.S. in Engineering Physics
- Type: elective
|
- Title of the course: Computational Intelligence
- Level: undergraduate
- Institute and departament: Connecticut College, Computer Science
- Short description of topics: Fuzzy logic, artificial neural networks, and genetic algorithms.
- Lecturer or responsible person: Gary Parker
- Language: English
- Starting year of the course in its present form: 2001
- Goals/contents of the course: Discuss how CI methods deal with vague, imprecise, and uncertain knowledge; learn from experience; self-organize; and adapt their behavior in response to changing conditions to solve real world problems. Use projects and the discussion of technical papers to cover methods of CI and their use.
- Approximate number of students: 10
- Intended audience: upper level CS majors
- Type: elective
|
- Title of the course: CS323 Artificial Intelligence
- Level: undergraduate
- Institute and departament: Department of Mathematics and Computer Science, South Carolina State University
- Short description of topics: 1. Classical AI: problems, search, games,reasoning, fuzzy reasoning. 2. Neural networks based AI: pattern recognition, learning, 3. Consequence-driven AI: advices, reinforcements, emotions. 4. Engineered Psychology: fundamental equation, limbic system
- Lecturer or responsible person: Stevo Bozinovski
- Language: English
- Starting year of the course in its present form: 2001
- Duration and period: Spring semester each year, 3 credits
- Approximate number of students: 15
- Intended audience: Computer Science Students
- The course is part of: B.S in Computer Science
- Type: elective
|
- Title of the course: CS496 Neuroinformatics and brain-computer interface
- Level: undergraduate
- Institute and departament: South Carolina State University
Mathematics and Computer Science Department
- Short description of topics: 1. Brains: Organization
2. Neuroinformatics websites
3. Brain signal processing
4. Controling devices using brain signals
- Lecturer or responsible person: Stevo Bozinovski
- Language: English
- Starting year of the course in its present form: 2006
- Duration and period: Spring semester each year, 3 credits
- Approximate number of students: 10
- Intended audience: Computer Science Students
- The course is part of: B.S. in Computer Science
- Type: elective
|
- Title of the course: Fuzzy Set Theory
- Level: Graduate/Undergraduate
- Institute and departament: University of South Florida
- Short description of topics: Fuzzy Sets, fuzzy logic, possibility theory, fuzzy control, fuzzy clustering, fuzzy learning, relation of fuzzy and probability.
- Lecturer or responsible person: Abraham Kandel
- Other people involved: Lawrence Hall
- Language: English
- Starting year of the course in its present form: 1988
- Goals/contents of the course: An overview of fuzzy sets and logic. Application areas are covered, such as control, learning, etc.
- Approximate number of students: 25
- Intended audience: Seniors or MS level students
- Type: Elective
|
- Title of the course: Topics in Intelligent Computing
- Level: graduate/postgraduate
- Institute and departament: University of Texas at El Paso, Department of Computer Science
- Short description of topics: Introduction to advanced concepts and techniques of intelligent and soft computing and their applications. Topics may include neural computations, fuzzy computations, evolutionary computations, intelligent control and intelligent web design. May be repeated for credit when topic varies.
- Language: English
- Web page: http://www.cs.utep.edu/vladik/cs5354.10
- The course is part of: M.Sc. and Ph.D. in Computer Science
- Type: elective
|
- Title of the course: Topics in Soft Computing
- Level: undergraduate
- Institute and departament: University of Texas at El Paso, Department of Computer Science
- Short description of topics: Introduction to basic concepts and techniques of soft computing, including neural, fuzzy, evolutionary, and interval computations, and their applications.
- Language: English
- Web page: http://www.cs.utep.edu/vladik/cs5354.10
- Duration and period: 1 semester, taught regularly
- Approximate number of students: 15-20
- The course is part of: B.Sc. in Computer Science
- Type: elective
|
|