Genetic Algorithms: Usefulness and Effectiveness for Pattern Recognition

Authors

Mohit Verma, Washington University in St Louis

Document Type

Technical Report

Publication Date

1991-05-01

Filename

WUCS-91-35.pdf

Technical Report Number

WUCS-91-35

Abstract

Genetic Algorithms have been gaining much interest since the early 1970's and have intrigued people from the fields of machine learning, artificial intelligence, neural networks and operations research. This paper describes the approach of genetic algorithms applied to neural networks. The experiments were conducted using various functions such as XOR,AND,SINE and different network sizes. Based on the experimental data, we concluded that for small network architectures represented by the functions (SINE,ENCODE,etc), genetic algorithms were not effective and the desired results were not achieved within a reasonable period of time.

Comments

Permanent URL: http://dx.doi.org/10.7936/K7VH5M5R

Recommended Citation

Verma, Mohit, "Genetic Algorithms: Usefulness and Effectiveness for Pattern Recognition" Report Number: WUCS-91-35 (1991). All Computer Science and Engineering Research.
https://openscholarship.wustl.edu/cse_research/653