Neural networks have been and will continue to be major research areas in artificial intelligence. Such models show promise in achieving human-like performance, particularly in areas such as speech and pattern recognition. Recently, neural networks have begun to find their way out of the research labs and into the realm of practical applications. Unfortunately, however, the study of such networks has been largely overlooked in the computer science undergraduate curriculum. Tomorrow's marketplace demands that computer science students be familiar with neural networks and with their problem solving abilities. This paper presents a proposal for a neural network module to be integrated into an Introduction to Artificial Intelligence course. Such a module proved to be a very popular and successful part of such a course given by the author. Sample projects assigned in the course will be presented. In a number of these projects, students either used microcomputer application software which simulates several neural network models or programmed their own simulations on microcomputers.
[1]
David Zipser,et al.
Feature Discovery by Competive Learning
,
1986,
Cogn. Sci..
[2]
James L. McClelland,et al.
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
,
1986
.
[3]
Stephen Grossberg,et al.
The ART of adaptive pattern recognition by a self-organizing neural network
,
1988,
Computer.
[4]
James L. McClelland.
Explorations In Parallel Distributed Processing
,
1988
.
[5]
Geoffrey E. Hinton,et al.
Learning internal representations by error propagation
,
1986
.
[6]
J J Hopfield,et al.
Neural networks and physical systems with emergent collective computational abilities.
,
1982,
Proceedings of the National Academy of Sciences of the United States of America.
[7]
W. Pitts,et al.
A Logical Calculus of the Ideas Immanent in Nervous Activity (1943)
,
2021,
Ideas That Created the Future.