Neural Networks

Spring 2016

Credits: 3

Level: Graduate, Optional

Prerequisite:

Hours: Friday, 7.45-14

Location: 302

Course Syllabus:

1-Introduction

2-Neuron Model and Network Architectures

3- Perceptron, Hamming Network and Hopfield Network

4-Perceptron Learning Rule

5-Supervised Hebbian Learning

6-Performance Surfaces

7-Performance Optimization

8-Widrow-Hoff Learning

9-Backpropagation

10-Variations on Backpropagation

Grading:

1. Homework and Projects: 50%

2. Mid-term exam: 25% (if any)

3. Final exam: 25%-50%

References:

1- Neural Network Design, Martin T. Hagan, Howard B. Demuth, Mark H. Beale, ISBN: 0-9717321-0-8

2-Neural Networks and Learning Machines, Simon S. Haykin, Prentice Hall, 2009

Power Points

Ch1 Ch2 Ch3

Ch4 Ch7 Ch8

Ch9 Ch10 Ch11

Ch12 MATLAB