TOP

Neural Networks and its Application

Spring 2006

 

last updated: 2006/03/22

1. Goal of Course

This course is provide of study by students features of different neural network models and its application for solving of different tasks, skill in programming of neural networks for solving of concrete task

 

2. Textbooks

* It use the presentation materials. You can download on the webboard.

* Contents of lectures:

Introduction. Different approaches to modeling and using of neural networks

Features of construction and working of brain

Binary neural network classifiers

    Logical neural networks

        Hemming neural network

Multi-Layer Neural networks.

    Forward neural networks

    Back propagation algorithm

    Different kinds of learning of MLP

    Using of MLP for forecasting of time series.

    Counterpropagation neural networks

    Recurrent multi-layer neural networks

    Using of recurrent multi-layer neural networks for recognition of grammatically correct sentences.

    Using of recurrent multi-layer neural networks for control of robots. LSTM-neural networks.

Radial basis functions

BAM/Hopfield associative memory

Adaptive resonance theory

    Architecture ART1

    Architecture ART2

    Architecture ARTMAP, FuzzyART

    Architecture MLP-ART

SOM

Spike neural networks.  

Using of Genetic Algorithms for learning and evolution of neural networks

New trends in development of neural networks

 

Condition for passing of midterm exam – selection of task for solving by NN,

Selection of kind of NN, learning method, training set, tool for implementation.

 

Condition of passing of final exam – implementation of NN and presentation of experiments with it.

 

3. Instructor

Name

Andrey Gavrilov  (Russia)

Contact Information
Tehephone : 031-201-2493
E-mail : avg@oslab.khu.ac.kr
Office :

Electronic & Information Building #B08

_material    

4. Tentative Schedule (tentative)

Kind

Title

Lecture 1

Introduction.

Different approaches to modeling and using of neural networks

Lecture 2

Features of construction and working of brain.

Lecture 3

Binary neural network classifiers

Lecture 4

Forward neural networks and back propagation learning algorithm

Lecture 5

Different kinds of learning of MLP

Colloquium 1

Using of MLP for forecasting of time series

Lecture 6

Counterpropagation neural networks

Lecture 7

Recurrent multi-layer neural networks

Colloquium 2

Using of recurrent multi-layer neural networks for control of robots. LSTM-neural networks.

Lecture 8

Radial basis functions

Lecture 9

BAM/Hopfield associative memory

Exam

MIDTERM EXAM

Lecture 10

Architecture ART1

Lecture 11

Architecture ART2

Lecture 12

Architecture ARTMAP

Colloquium 3

Architecture MLP-ART

Lecture 13

SOM

Lecture 14

Usage of unsupervised neural networks

Lecture 15

Spike neural networks

Lecture 16

Using of Genetic Algorithms for learning and evolution of neural networks

Lecture 17

Usage of neural networks for recognition of visual images

Lecture 18

Future of neural networks

Presentations 1

Presentations 2

Presentations 3

Presentation 4

Exam

 FINAL EXAM

You can download here:

 

5. Grading Policy

Midterm

Final

Project  (Homework and presentation)

Total

20%

40%

40%

100%

 

 

6. Suggested reading

  1. Arbib, M. A. The Metaphorical Brain. New York: Wiley (1990).
  2. Bishop C. Neural Networks for pattern recognition. Clarendon Press, Oxford (1995).
  3. Fausett L. Fundamentals of Neural Networks. Prentice Hall (1994)
  4. Hassoun M. Fundamentals of Artificial Neural Networks. MIT Press (1995).
  5. Hawkins J., Blakeslee S. On Intelligence. 2005. (Electronic version is available).
  6. Honavar, V. & Uhr, L. (Ed.) Artificial Intelligence and Neural Networks: Steps Toward Principle Integration. San Diego, CA: Academic Press (1994).
  7. Hristev R.M. Artificial Neural Networks. (Electronic book is available).
  8. Jones M.T. AI application Programming. Charles River Media, Inc., Hingham, Massachusetts (2003).
  9. Kecman V. Learning and Soft Computing. MIT, 2001. (Electronic book is available).
  10. Krose B., van der Smagt P. An Introduction to Neural Networks. 1996 (Electronic book is available).
  11. Lindsey C.S. Neural Networks in Hardware: Architectures, Products and Applications. Lectures, Electronic Book. Royal Institute of Technology Stockholm, Sweden, (2002).
  12. Lawrence J. Introduction to Neural Networks. California Scientific, Nevada City, (1993).
  13. Luger G.F. Artificial Intelligence. Structures and Strategies for Complex Problem Solving. Addison Wesley  (2002). (Electronic content of separate parts is available).
  14. Mind Design II. Philosophy, psychology, artificial intelligence. Eds.  J.Haugeland. MIT Press, 1997 (Electronic book is available).
  15. Minsky, M. Society of Mind. New York: Basic Books (1986).
  16. Mitchell T. Machine Learning. MacGraw Hill (1997).
  17. Negnevitsky M. Artificial Intelligence. A guide to intelligent systems. Addison-Wesley, 2005.
  18. Nilsson, N., The Mathematical Foundations of Learning Machines, San Francisco: Morgan Kaufmann (1990).
  19. Rabunal J.R., Dorado J. Artificial Neural Networks in Real Life Applications. IDEA Group Publishing, 2006. (Electronic book is available).
  20. Russel, S. & Norvig, P., Artificial Intelligence - a modern approach. Englewood Cliffs, NJ: Prentice Hall (2002). (Electronic book is available).
  21. Sutton R.S., Barto A.J. Reinforcement Learning: An Introduction. The MIT Press Cambridge, Massachusetts, London. (Electronic book is available).
  22. The Handbook of Brain Theory and Neural Networks. – Eds. M.A. Arbib, MIT Press, 2003 (Electronic version is available).
  23. Veelenturf L.P.J. Analysis and Applications of Artificial Neural Networks. Prentice Hall, 1995. (Electronic version is available).
  24. Wasserman, P. Advanced Methods in Neural Computing. New York: Van Nostrand Rheinhold (1993).

 

  topicon.gif