Evolutionary Neural Trees*

An evolutionary learning method for modeling and prediction of complex systems is described and applied to an environmental system. The method is based on tree-structured neural networks whose node type, weight, size and topology are dynamically adapted by genetic algorithms. Since the genetic algorithm used for training does not require error derivatives, a wide range of neural models can be identified. The application of this method to the prediction of water pollution shows comparable results to those achieved by well-engineered, conventional system-identification methods. ·rn Pmc. Int. Joint Conf on Artificial Intelligence (IJCAI) W01·kshop on AI and the Envimmnent, Montreal, Canada, August 20-25, 1995. This research was supported in part by the Real-World Computing Program under the project SIFOGA.

[1]  Peter Secretan.  Learning , 1965, Mental Health.

[2]  A. G. Ivakhnenko,et al.  Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..

[3]  Mark A. Franklin,et al.  A Learning Identification Algorithm and Its Application to an Environmental System , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[5]  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.

[6]  Heinz Mühlenbein,et al.  Predictive Models for the Breeder Genetic Algorithm I. Continuous Parameter Optimization , 1993, Evolutionary Computation.

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

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

[9]  Thomas Bäck,et al.  An Overview of Evolutionary Algorithms for Parameter Optimization , 1993, Evolutionary Computation.

[10]  Byoung-Tak Zhang,et al.  Effects of Occam's Razor in Evolving Sigma-Pi Neural Nets , 1994, PPSN.

[11]  Byoung-Tak Zhang,et al.  Synthesis of sigma-pi neural networks by the breeder genetic programming , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.