## CS 6673 Neural Network
Computing (1472I), Spring 2009

This course gives an
introduction to neural network models and their applications. Organization and
learning in neural network models including perceptrons,
adalines, backpropagation networks,
recurrent networks, adaptive resonance theory and the neocognitron
are discussed. Application in areas such as decision systems, nonlinear control,
speech processing and vision is explored.

The pre-requisite for this course
is CS 540 or its equivalent. Undergraduate student may take this course if they
have already taken CS 1114,
and the undergraduate math sequence.

**Instructor** :

K. Ming Leung

**E-mail :**

mleung@duke.poly.edu

**Office** :

LC 127

**Office hours :**

**Monday: **2:00
- 3:00 pm
**Wednesday: **4:00
- 500 pm
**Friday: **10:00
- 11:00 pm, noon – 1:00 pm

**Textbook** :

"Neural Network Design",
by Martin T. Hagan, Howard B. Demuth, Mark H. Beale, ISBN-10: 0-9717321-0-8.

**Classroom** :

RH 317

**Grading System (Tentative)**:

Attendance/Participation (5%), HW
(35%), Midterm-Exam (30%), Project (30%).

**Lecture Notes :**

Introduction:

Introduction to Artificial Neuron
Networks.

Neural Networks for Pattern
Classification.

Perceptron for Pattern Classification.

ADALINE for Pattern Classification.

Backpropagation for
Multilayer Neural Network

Learning Vector Quantization.

Neural Networks for Pattern Association

Iterative Bidirectional Memory

Iterative Discrete Hopfield Net

Hamming Net

Self-Organized Map

Adaptive Resonance Theory 1

**Assignments** :

**HW01 (**Due February 10**)**

**HW02 **(Due March 3)

**HW03 **(Due March 24): Solution

**HW04 **(Due March 24): Solution

HW05 (Due April 14)

HW06 (Due May 5)

HW07 (Due April 28)

**Midterm**: (open book midterm) April 7.