Cooperative-Competitive Algorithms for Evolutionary Networks Classifying Noisy Digital Images |
| |
Authors: | Brown AD Card HC |
| |
Affiliation: | (1) Dept. of Electrical & Computer Engineering, The University of Manitoba, R3T 5V6 Winnipeg, Manitoba, Canada |
| |
Abstract: | We describe an efficient method of combining the global search of genetic algorithms (GAs) with the local search of gradient descent algorithms. Each technique optimizes a mutually exclusive subset of the network's weight parameters. The GA chromosome fixes the feature detectors and their location, and a gradient descent algorithm starting from random initial values optimizes the remaining weights. Three algorithms having different methods of encoding hidden unit weights in the chromosome are applied to multilayer perceptrons (MLPs) which classify noisy digital images. The fitness function measures the MLP classification accuracy together with the confidence of the networks. |
| |
Keywords: | artificial neural networks genetic algorithms evolutionary networks adaptive image processing |
本文献已被 SpringerLink 等数据库收录! |