Neural Networks 2

Garant předmětu:

Lecturer:

Tutor:

Supervisor:

Department of Software Engineering

Synopsis:

The second module is oriented first to multi-layer neural networks and next to self-organized artificial neural networks. The biological context, cluster analysis and principal component analysis are used for self-organized artificial neural network realization. Self-organization is discussed both in vector and metric spaces.

Requirements:

Basic knowledges from linear algebra.

Syllabus of lectures:

1.Multi-layer perceptron, universal approximation, backpropagation.

2.Vector space with Minkowski metrics.

3.Metric space of strings.

4.Cluster analysis in vector space.

5.Cluster analysis in metric space.

6.Self-organization, patterns, etalons.

7.SOM as extended cluster analysis.

8.SOM topology, SOM as transformation.

9.Kohonen learning of SOM.

10.SOM learning in metric space.

11.Traditional principal component analysis.

12. Introduction to deep learning.

Syllabus of tutorials:

1.Multi-layer perceptron, universal approximation, backpropagation.

2.Vector space with Minkowski metrics.

3.Metric space of strings.

4.Cluster analysis in vector space.

5.Cluster analysis in metric space.

6.Self-organization, patterns, etalons.

7.SOM as extended cluster analysis.

8.SOM topology, SOM as transformation.

9.Kohonen learning of SOM.

10.SOM learning in metric space.

11.Traditional principal component analysis.

12. Introduction to deep learning.

Study Objective:

Knowledge:

Mutli-layer perceptron, cluster analysis, self-organized artificial neural networks, basis of deep learning.

Abilities:

Use of mutli-layer perceptron, use of cluster analysis, use of self-organization, use of deep learning for classification.

Study materials:

Compulsory literature:

[1] J. Šíma, R. Neruda: Teoretické otázky neuronových sítí, Matfyzpress, Praha, 1996.

[2] M. Šnorek: Neuronové sítě a neuropočítače, ČVUT, Praha 2002

Recommended literature:

[3] S. Haykin: Neural Networks, Macmillan, New York, 1994.

[4] L.V. Fausett: Fundamentals of Neural Networks: Architectures, Algorithms and Applications, Prentice Hall, New Jersey, 1994.

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans:

• Applications of Informatics in Natural Sciences (elective course)