Cooperative Coevolution of Neural Networks and Ensembles of Neural Networks

Cooperative coevolution is a recent paradigm in the area of evolutionary computation focused on the evolution of coadapted subcomponents without external interaction. In cooperative coevolution a number of species are evolved together. The cooperation among the individuals is encouraged by rewarding the individuals according to their degree of cooperation in solving a target problem. The work on this paradigm has shown that cooperative coevolutionary models present many interesting features, such as specialization through genetic isolation, generalization and efficiency. Cooperative coevolution approaches the design of modular systems in a natural way, as the modularity is part of the model. Other models need some a priori knowledge to decompose the problem by hand. In most cases, either this knowledge is not available or it is not clear how to decompose the problem. This chapter describes how cooperative coevolution can be applied to the evolution of neural networks and ensembles of neural networks. Firstly, we present a model that develops subnetworks (modules) instead of whole networks. These modules are combined making up a network, by means of a cooperative coevolutionary algorithm. Secondly, we present a general framework for designing neural network ensembles by means of cooperative coevolution. The proposed model has two main objectives: first, the improvement of the combination of the trained individual networks; second, the cooperative evolution of such networks, encouraging collaboration among them, instead of a separate training of each network. In addition, a population of ensembles is evolved, improving the combination of networks and obtaining subsets of networks to form ensembles that perform better than the combination of all the evolved networks. We also show how the multiobjective evaluation of the fitness of modules, networks, and ensembles can improve the performance of the model. For each element (module, network, and ensemble), different objectives are defined, considering not only its performance in the given problem, but also its cooperation with the rest of the networks. The results show the usefulness of the multiobjective approach.

[1]  T. W. Anderson.  An Introduction to Multivariate Statistical Analysis , 1959 .

[2]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

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

[4]  Risto Miikkulainen,et al.  Forming Neural Networks Through Efficient and Adaptive Coevolution , 1997, Evolutionary Computation.

[5]  Robert F. Port,et al.  Fractally configured neural networks , 1991, Neural Networks.

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

[7]  Robert L. Winkler,et al.  Limits for the Precision and Value of Information from Dependent Sources , 1985, Oper. Res..

[8]  César Hervás-Martínez,et al.  Cooperative coevolution of artificial neural network ensembles for pattern classification , 2005, IEEE Transactions on Evolutionary Computation.

[9]  Paul J. Werbos,et al.  The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting , 1994 .

[10]  Geoffrey E. Hinton,et al.  Simplifying Neural Networks by Soft Weight-Sharing , 1992, Neural Computation.

[11]  Ling Guan,et al.  Modularity in neural computing , 1999, Proc. IEEE.

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

[13]  Dušan Petrovački,et al.  Evolutional development of a multilevel neural network , 1993, Neural Networks.

[14]  Vasant Honavar,et al.  Generative learning structures for generalized connectionist networks , 1990 .

[15]  Lothar Thiele,et al.  Multiobjective Optimization Using Evolutionary Algorithms - A Comparative Case Study , 1998, PPSN.

[16]  Peter M. Williams,et al.  Bayesian Regularization and Pruning Using a Laplace Prior , 1995, Neural Computation.

[17]  Stephen I. Gallant,et al.  Neural network learning and expert systems , 1993 .

[18]  Padraig Cunningham,et al.  Using Diversity in Preparing Ensembles of Classifiers Based on Different Feature Subsets to Minimize Generalization Error , 2001, ECML.

[19]  M. Ishikawa,et al.  A structural learning algorithm with forgetting of link weights , 1989, International 1989 Joint Conference on Neural Networks.

[20]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[21]  Xin Yao,et al.  Evolutionary ensembles with negative correlation learning , 2000, IEEE Trans. Evol. Comput..

[22]  Xin Yao,et al.  Evolving a cooperative population of neural networks by minimizing mutual information , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[23]  David W. Opitz,et al.  Actively Searching for an E(cid:11)ective Neural-Network Ensemble , 1996 .

[24]  Lakhmi C. Jain,et al.  Neural Network Training Using Genetic Algorithms , 1996 .

[25]  David E. Goldberg,et al.  Genetic Algorithms with Sharing for Multimodalfunction Optimization , 1987, ICGA.

[26]  Kalyanmoy Deb,et al.  Muiltiobjective Optimization Using Nondominated Sorting in Genetic Algorithms , 1994, Evolutionary Computation.

[27]  David B. Fogel,et al.  Evolving artificial intelligence , 1992 .

[28]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[29]  Benjamin W. Wah,et al.  Global Optimization for Neural Network Training , 1996, Computer.

[30]  C. Fonseca,et al.  GENETIC ALGORITHMS FOR MULTI-OBJECTIVE OPTIMIZATION: FORMULATION, DISCUSSION, AND GENERALIZATION , 1993 .

[31]  Risto Miikkulainen,et al.  Efficient Reinforcement Learning through Symbiotic Evolution , 2004 .

[32]  G. Yule.  On the Association of Attributes in Statistics: With Illustrations from the Material of the Childhood Society, &c , 1900 .

[33]  K. Saito,et al.  Cooperative co-evolutionary algorithm-how to evaluate a module? , 2000, 2000 IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks. Proceedings of the First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks (Cat. No.00.

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

[35]  Kenneth Alan De Jong,et al.  An analysis of the behavior of a class of genetic adaptive systems. , 1975 .

[36]  Bruce A. Whitehead,et al.  Cooperative-competitive genetic evolution of radial basis function centers and widths for time series prediction , 1996, IEEE Trans. Neural Networks.

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

[38]  David R. Jefferson,et al.  Selection in Massively Parallel Genetic Algorithms , 1991, ICGA.

[39]  M van der Borst.  Local Structure Optimization in Evolutionary Generated Neural Network Architectures , 1994 .

[40]  D. Opitz,et al.  Popular Ensemble Methods: An Empirical Study , 1999, J. Artif. Intell. Res..

[41]  L. Cooper,et al.  When Networks Disagree: Ensemble Methods for Hybrid Neural Networks , 1992 .

[42]  Sung-Bae Cho,et al.  Evolutionary Learning of Modular Neural Networks with Genetic Programming , 1998, Applied Intelligence.

[43]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[44]  Michael Conrad,et al.  Combining evolution with credit apportionment: A new learning algorithm for neural nets , 1994, Neural Networks.

[45]  Kenneth A. De Jong,et al.  Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents , 2000, Evolutionary Computation.

[46]  Vasant Honavar,et al.  Generative learning structures and processes for generalized connectionist networks , 1993, Inf. Sci..

[47]  Ludmila I. Kuncheva,et al.  Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy , 2003, Machine Learning.

[48]  César Hervás-Martínez,et al.  Multi-objective cooperative coevolution of artificial neural networks (multi-objective cooperative networks) , 2002, Neural Networks.

[49]  David E. Goldberg,et al.  Implicit Niching in a Learning Classifier System: Nature's Way , 1994, Evolutionary Computation.

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

[51]  Xin Yao,et al.  Simultaneous training of negatively correlated neural networks in an ensemble , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[52]  Bruce E. Rosen,et al.  Ensemble Learning Using Decorrelated Neural Networks , 1996, Connect. Sci..

[53]  Xin Yao,et al.  Ensemble learning via negative correlation , 1999, Neural Networks.

[54]  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.

[55]  Michael Georgiopoulos,et al.  Coupling weight elimination with genetic algorithms to reduce network size and preserve generalization , 1997, Neurocomputing.

[56]  Vittorio Maniezzo,et al.  Genetic evolution of the topology and weight distribution of neural networks , 1994, IEEE Trans. Neural Networks.