Evolving neural networks using a dual representation with a combined crossover operator

A new approach to the evolution of neural networks is presented. A linear chromosome combined with a grid-based representation of the network, and a new crossover operator, allow the evolution of the architecture and the weights simultaneously. In the approach there is no need for a separate weight optimization procedure and networks with more than one type of activation function can be evolved. A pruning strategy is also introduced, which leads to the generation of solutions with varying degrees of complexity. Results of the application of the method to several binary classification problems are reported.

[1]  L. D. Whitley,et al.  Genetic Reinforcement Learning for Neurocontrol Problems , 2004, Machine Learning.

[2]  Byoung-Tak Zhang,et al.  Genetic Programming of Minimal Neural Nets Using Occam's Razor , 1993, ICGA.

[3]  Byoung-Tak Zhang,et al.  Evolving Optimal Neural Networks Using Genetic Algorithms with Occam's Razor , 1993, Complex Syst..

[4]  Sam Kwong,et al.  Genetic structure for NN topology and weights optimization , 1995 .

[5]  Colin Campbell,et al.  The Target Switch Algorithm: A Constructive Learning Procedure for Feed-Forward Neural Networks , 1995, Neural Computation.

[6]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[7]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[8]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[9]  L. Darrell Whitley,et al.  Genetic algorithms and neural networks: optimizing connections and connectivity , 1990, Parallel Comput..

[10]  Riccardo Poli,et al.  Some Steps Towards a Form of Parallel Distributed Genetic Programming , 1996 .

[11]  R. Poli,et al.  Discovery of Symbolic, Neuro-Symbolic and Neural Networks with Parallel Distributed Genetic Programming , 1997, ICANNGA.

[12]  Heinrich Braun,et al.  ENZO-M - A Hybrid Approach for Optimizing Neural Networks by Evolution and Learning , 1994, PPSN.

[13]  Xin Yao,et al.  A Preliminary Study on Designing Artiicial Neural Networks Using Co-evolution , 1995 .

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

[15]  J. R. McDonnell,et al.  Evolving neural network connectivity , 1993, IEEE International Conference on Neural Networks.

[16]  Riccardo,et al.  Evolution of the Topology and the Weightsof Neural Networks using GeneticProgramming with a Dual RepresentationJo , 1997 .

[17]  D. B. Fogel,et al.  Using evolutionary programing to create neural networks that are capable of playing tic-tac-toe , 1993, IEEE International Conference on Neural Networks.

[18]  D. R. McGregor,et al.  Designing application-specific neural networks using the structured genetic algorithm , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.