Softcomputing

The course is a substitute for:

Softcomputing (X33SCP)

Lecturer:

Tutor:

Supervisor:

Department of Cybernetics

Synopsis:

The aim of this course is to get the students knowledgeable with non-traditional computational techniques of optimisation, state-space search, control and decision-making. Many of the softcomputing methods utilise analogies with various phenomena in nature and/or society. Results obtained by these methods often have a high quality, but their absolute reliability is never guaranteed. During the seminars the students will get a chance to get basic practical skills with a sample softcomputing problem.

Requirements:

Requirements to pass:

1. Hand in the assignment on EAs (max 10 points)

2. Hand in the assignment on NN (max 5 points)

3. Test (max 15 points)

4. In each of the above tasks, you have to earn at least 1/3 of its respective maximal number of points.

5. If you hand in the assignment after deadline, your score will be decreased by 2 points a week.

Grading:

1. Excellent (25,30> points

2. Very good (20,25> points

3. Good (15,20> points

4. Did not pass (0,15> points

Syllabus of lectures:

1. Introduction to softcomputing methods, relationship to phenomena known from other scientific fields

2. Fuzzy sets and fuzzy logics

3. Fuzzy logics and decision-making

4. Fuzzy control

5. Neural networks - basic principles, their learning and set-up

6. Neural networks with backward propagation

7. Kohonen's learning networks

8. Evolutionary computing - basic principles and operators

9. Genetic algorithms - function principles

10. Genetic algorithms - problem representation, convergence

11. Genetic algorithms in constrained problems, special representations

12. Genetic programming - principles and comparison with genetic algorithms

13. Specific problems of evolutionary computing techniques, softcomputing applications

14. Summary (spare space)

Syllabus of tutorials:

1. Organisational matters, seminars/labs detailed contents

2. Softcomputing in general

3. Fuzzy logics principles

4. Fuzzy logics for control and decision-making - part 1.

5. Fuzzy logics for control and decision-making - part 2.

6. Neural networks - part 1.

7. Neural networks - part 2.

8. Neural networks - part 3.

9. Evolutionary computing (EC) - basic operators, their implementation, individual task of EC given

10. Individual work on the EC task - part 1.

11. Individual work on the EC task - part 2.

12. Individual work on the EC task - part 3.

13. Presentation of individual work results - discussion on the results

14. Summary, (spare space)

Study Objective:

Study materials:

Recommended reading:

1. Goldberg: Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989

2. Michalewicz: Genetic Algorithms + Data Structures = Evolution Programs, Springer, 1998

3. Michalewicz: How to solve it? Modern heuristics. 2nd ed. Springer, 2004.

4. Bishop: Neural Networks for Pattern Recognition, Oxford University Press, 1995

5. Hájek: Mathematics of Fuzzy Logic. Kluwer, 1998

There is no text-book covering the course completely; the lecturer will hint resources to particular topics.

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans:

• Computer Science and Engineering (elective course)