Syllabus of Neural Network I

Neural Network I: Fundamental Theory and Applications (CSA01)
(For Graduate School)

Year: 1st and 2nd
Quarter : 1st
Time: Wed-1, Wed-2
Meeting Place : M12

Instructor:

Qiangfu Zhao
Office:102A
Phone: 3214
Email: qf-zhao@u-aizu.ac.jp

Course Description:

A system must have at least three abilities in order to be intelligent:

it must be able to acquire information by itself,
it must have a structure which is flexible enough to represent and integrate information, and
It must have a mechanism to adapt itself to the environment using the acquired information.

The goal of neural network research is to realize an artificial intelligent system using the human brain as the model. Accordingly, there are three basic problems in this area:

What kind of structure or model should we use?
How to train or design the neural networks?
How to use neural networks for knowlege acquisition?

This course introduces the basic models, learning algorithms, and some applications of neural networks. After this course, we should be able to know how to use neural networks for solving different problems related to pattern recognition, function approaximation, data visualization, and so on.

Course objectives:

In this course, we will study the following topics:

Basic neuron models: McCulloch-Pitts model and the generalized one, distance or similarity based neuron model, radial basis function model, etc.
Basic neural network models: multilayer perceptron, distance or similarity based neural networks, associative memory and self-organizing feature map, radial basis function based multilayer perceptron, neural network decision trees, etc.
Basic learning algorithms: the delta learning rule, the back propagation algorithm, self-organization learning, the r4-rule, etc.
Applications: pattern recognition, function approximation, information visualization, etc.

Class Schedule:

Class Schedule
Class ID	Date and Time	Contents
1	April 9, 9:00 - 10:30	Introduction
2	April 9, 10:40 - 12:10	Fundamental concepts: neuron models and basic learning rules
3	April 16, 9:00 - 10:30	Team project I: Learning of a single neuron and single layer neural networks Part one: Learning of a singale neuron Part two: Learning of single layer neural networks
4	April 16, 10:40 - 12:10	Multilayer neural networks and back-propagation
5	April 23, 9:00 - 10:30	Team Project II: Learning of multilayer neural networks
6	April 23, 10:40 - 12:10	Associative memory
7	April 30, 9:00 - 10:30	Team Project III: Image restoration based on associate memory
8	April 30, 10:40 - 12:10	Self-organizing neural networks
9	May 7, 9:00 - 10:30	Team Project IV: Learning of self-organizing neural network
10	May 7, 10:40 - 12:10	Self-organizing feature map
11	May 14, 9:00 - 10:30	Team Project V: Data visualization with self-organizing feature map Data for Project V
12	May 14, 10:40 - 12:10	RBF neural networks and support vector machines
13	May 28, 9:00 - 10:30	Team Project VI: SVM based learning
14	May 28, 10:40 - 12:10	Neural Network Trees
15	June 4, 9:00 - 10:30	Team Project VII: Neural network tree based learning
16	June 11, 9:00 - 10:30	Presentation of project results.

References:

Jacek M. Zurada, Introduction to Artificial Neural Systems, PWS Publishing Company, 1995.
Simon Haykin, Neural Networks: A Comprehensive Foundation, Macmillan College Publishing Company, 1994.
Mohamad H. Hassoun, Foundamentals of Artificial Neural Networks, The MIT Press, 1995.
Laurene Fausett, Fundamentals of Neural Networks: Architectures, Algorithms, and Applications, Prentice Hall International, Inc., 1994.
B. D. Ripley, Pattern Recognition and Neural Networks, Cambridge University Press., 1996.

Evaluation:

Attendance: 16
Team project: 84 (12 x 7)