The course introduces the foundations of artificial neural networks, genetic algorithms, fuzzy systems, swarm intelligence, and hybridizations of the above techniques. This domain is called Computational Intelligence, and it is a numerical interpretation of biological intelligence.
Preliminaries (2 hours)
Basic Concepts (6 hours)
Single-Layer Perceptrons as Classifiers (5 hours)
Multi-Layer Feedforward Networks (6 hours)
Single-Layer Feedback Networks (6 hours)
Associative Memories (5 hours)
Self-Organizing Networks (6 hours)
Genetic Algorithms (3 hours)
Swarm Intelligence (2 hours)
Fuzzy Logic (3 hours)
Fuzzy Neural Networks (2 hours)
Radial Basis Function Neural Networks (2 hours)
The Power and Computational Complexity of Neural Networks (2 hours)
Epistemological Considerations of Neural Computing (2 hours)
We are going to use results presented in several textbooks and journal papers. Just to make your life easy, here are the recommended textbooks:
Cataron, A. Computational
Intelligence (in Romanian),
Zurada, J. Introduction
to Artificial Neural Systems. West Publishing Company,
Haykin, S. Neural
Networks - A Comprehensive Foundation. Macmillan College Publishing
M. T. Hagan, H. B.
Demuth, M. Beale, Neural Network Design, PWS Publishing Co.,
Rao, V. C++ Neural Networks and Fuzzy Logic, M&T Books, IDG Books Worldwide, Inc., 1995. This book can be used as a handbook for neural OOP implementations. It can be downloaded from http://freebooks.by.ru/
DSI Neural Networks Group is a very complete source of electronic information
Gurney's Notes help you to learn about the basic concepts and ideas in artificial neural networks
Machine Learning Datasets is a very good source of benchmarks for testing your neural implementations.
Ant Colony Optimization is a source of tutorials.