2DELTA-GANN: A NEW APPROACH TO TRAINING NEURAL NETWORKS USING GENETIC ALGORITHMS

We describe a method of using Genetic Algorithms for training multi-layer perceptron neworks in which the chromosomes encode \rules" for changing the network weights rather than the weights themselves. The genetic operators of crossover, selection and mutation are used to generate new rules which are then applied to the weight matrix. The approach is signican tly better than other approaches to training networks using genetic algorithms and successfully solves a number of benchmark problems which are known to be dicult for backward error propagation.

[1]  J. D. Schaffer,et al.  Combinations of genetic algorithms and neural networks: a survey of the state of the art , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[2]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[3]  W. Spears,et al.  On the Virtues of Parameterized Uniform Crossover , 1995 .

[4]  Lawrence Davis,et al.  Training Feedforward Neural Networks Using Genetic Algorithms , 1989, IJCAI.

[5]  L. Darrell Whitley,et al.  Optimizing Neural Networks Using FasterMore Accurate Genetic Search , 1989, ICGA.

[6]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[7]  G. Kane Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol 1: Foundations, vol 2: Psychological and Biological Models , 1994 .

[8]  L. Darrell Whitley,et al.  The GENITOR Algorithm and Selection Pressure: Why Rank-Based Allocation of Reproductive Trials is Best , 1989, ICGA.

[9]  Gilbert Syswerda,et al.  Uniform Crossover in Genetic Algorithms , 1989, ICGA.

[10]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[11]  L. Darrell Whitley,et al.  Delta Coding: An Iterative Search Strategy for Genetic Algorithms , 1991, ICGA.

[12]  Richard K. Belew,et al.  Evolving networks: using the genetic algorithm with connectionist learning , 1990 .