Evolving Neural Networks for Decomposable Problems Using Genetic Programming

Many traditional methods for training neural networks using genetic algorithms and genetic programming do not have any special provisions for taking advantage of decomposable problems which can be solved by combining solutions to each subproblem. This paper describes a new approach to neural network construction using genetic programming which is designed to rapidly construct networks composed of similar subnetworks. A system has been developed to produce trained weightless neural networks by using construction rules to build the networks. The network construction rules are evolved by the genetic programming system. The system has been applied to decomposable Boolean problems and the results were compared with a modified version of the system in which networks cannot be constructed modularly. The modular version of the system obtains significantly better results than the nonmodular version of the program.

[1]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[2]  Peter M. Todd,et al.  Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

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

[4]  Jan Torreele,et al.  Temporal Processing with Recurrent Networks: An Evolutionary Approach , 1991, ICGA.

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

[6]  Toshio Fukuda,et al.  Dynamic memory by recurrent neural network and its learning by genetic algorithm , 1993, Proceedings of 32nd IEEE Conference on Decision and Control.

[7]  Xin Yao,et al.  Evolutionary Artificial Neural Networks , 1993, Int. J. Neural Syst..

[8]  L. Darrell Whitley,et al.  Genetic Reinforcement Learning with Multilayer Neural Networks , 1991, ICGA.

[9]  Leslie J. Kitchen,et al.  Evolving Modular Neural Networks Using Rule-Based Genetic Programming , 1999, Australian Joint Conference on Artificial Intelligence.

[10]  Richard J. Duro,et al.  Evolutionary generation and training of recurrent artificial neural networks , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[11]  Tariq Samad,et al.  Towards the Genetic Synthesisof Neural Networks , 1989, ICGA.

[12]  D. Parisi,et al.  “Genotypes” for neural networks , 1998 .

[13]  Martin Mandischer,et al.  Representation and Evolution of Neural Networks , 1993 .