Neural Networks and Neurocomputers

The course is a substitute for:

Neural Nets and Neurocomputers (X36NAN)

Lecturer:

Tutor:

Supervisor:

Department of Computer Science and Engineering

Synopsis:

Introduction, basic terminology. Hopfield's net. Perceptron, multilevel perceptron, Adaline/Madaline. Back-propagation. Kohonen's net, LVQ1, LVQ2, LVQ3. ART net, Carpenter-Grossberg classifier. Boltzmann machine. Applications: prediction by means of neural nets, expert systems, image processing, data compression. Neural hardware, neurochips, neural accelerators. Software simulators, introduction to NeuralWorks Professional II/Plus.

Requirements:

Syllabus of lectures:

1. Introduction into neural nets

2. Hopfield´s net

3. Back-propagation neural net

4. Kohonen´s net

5. Simulation, SW products

6. Paradigm classification

7. Time series prediction

8. Neural nets and image processing

9. Neural regulators

10. Selforganizing neural nets

11. Data compression

12. HW accelerators

13. Boltzman machine

14. Reserve

Syllabus of tutorials:

1. - 13. Will be organized according the number of participants (Individual neural net project implemented in NEURALWORKS PROFESSIONAL II/PLUS)

14. Credit

Study Objective:

Study materials:

[1] Haykin, S.: Neural Networks. IEEE Computer Society Press 1994

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans: