M,W,F 9:10-10, Stocker r. 166
Professor: Dr. Janusz Starzyk Spring Quarter 2001

Prereq. EE 715 or permission

Text

Marc M. Van Hulle, "Faithful Representations and Topographic Maps: From Distortion- to Information-Based Self-Organization"
John Wiley & Sons; 2000.

References

C. Mead, "Analog VLSI and Neural Systems", Addison-Wesley, 1989.

Course Description

This course discusses advanced concepts of self-organizing neural networks - that is networks of elemental processors interconnected like their biological
models. Neural-net implementations of pattern recognition algorithms provide important, practical advantages by allowing fast realization of parallel,
iterative procedures. Operations of neural networks will be developed and used for different neural functions. An example self-organizing neural system
simulating biological systems will be examined. The emphais in this course is on development of the concept of self-organizing neural system with locally
interconnected processing components.  Students will simulate neural networks for patter recognition and classification using PC software tools.

Office hours

T,Th 2-3, other hours by appointment. Office location - Stocker 347.

email: starzyk@bobcat.ent.ohiou.edu, phone 593-1580.

Grading

Grades will be based on the following;

Homework (30%)
Design project (40%)
Classroom presentation (30%)

Withdrawal

A student may withdraw from class at his discretion up to and including the first 21 days of the quarter.

Academic Conduct

Cheating, submitting work of other students as your own, or plagiarism in any form will result in penalties ranging from an F on the assignment to expulsion
from the university, depending on the seriousness of the offense.