A Novel Similarity-Based Crossover for Artificial Neural Network Evolution

This work presents an evolutionary approach for the optimization of neural networks design, based on the joint evolution of the topology and the connection weights, providing a novel similarity-based crossover that aims to overcome one of the major problems of this operator, known as the permutation problem. The approach has been implemented and applied to two benchmark classification problems in machine learning, and the experimental results, compared to those obtained by other works in the literature, show how it can produce compact neural networks with a satisfactory generalization capability.

[1]  Peter J. B. Hancock,et al.  Genetic algorithms and permutation problems: a comparison of recombination operators for neural net structure specification , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[2]  Antonia Azzini,et al.  Evolving neural networks for static single-position automated trading , 2008 .

[3]  Tamás D. Gedeon,et al.  Exploring constructive cascade networks , 1999, IEEE Trans. Neural Networks.

[4]  David J. Spiegelhalter,et al.  Machine Learning, Neural and Statistical Classification , 2009 .

[5]  Ajith Abraham,et al.  Engineering Evolutionary Intelligent Systems , 2008, Studies in Computational Intelligence.

[6]  Xin Yao,et al.  A new evolutionary system for evolving artificial neural networks , 1997, IEEE Trans. Neural Networks.

[7]  Antonia Azzini,et al.  A New Genetic Approach for Neural Network Design , 2008, Engineering Evolutionary Intelligent Systems.

[8]  Md. Monirul Islam,et al.  Graph Matching Recombination for Evolving Neural Networks , 2007, ISNN.

[9]  S Usui,et al.  Robustness, evolvability, and optimality of evolutionary neural networks. , 2005, Bio Systems.

[10]  Asim Roy,et al.  An algorithm to generate radial basis function (RBF)-like nets for classification problems , 1995, Neural Networks.

[11]  David B. Fogel,et al.  The Advantages of Evolutionary Computation , 1997, BCEC.

[12]  César Hervás-Martínez,et al.  COVNET: a cooperative coevolutionary model for evolving artificial neural networks , 2003, IEEE Trans. Neural Networks.

[13]  César Hervás-Martínez,et al.  An alternative approach for neural network evolution with a genetic algorithm: Crossover by combinatorial optimization , 2006, Neural Networks.

[14]  Jihoon Yang,et al.  Constructive Neural-Network Learning Algorithms for Pattern Classification , 2000 .

[15]  Stefan Haflidason.  On the significance of the permutation problem in neuroevolution , 2009, GECCO '09.

[16]  Derong Liu,et al.  Advances in Neural Networks - ISNN 2007, 4th International Symposium on Neural Networks, ISNN 2007, Nanjing, China, June 3-7, 2007, Proceedings, Part I , 2007, ISNN.

[17]  O. Mangasarian,et al.  Robust linear programming discrimination of two linearly inseparable sets , 1992 .