Aprendizado Genético: Operadores de Crossover Naturais Aprimorados
Resumo
Aguilar-Ruiz et al propuseram operadores de crossover para dados contínuos e discretos utilizado a representação natural. Eles apresentaram vantagens na precisão e na eficiência em comparação com a representação binária. Entretanto, estes operadores não exploram o espaço de busca como o operador binário de dois pontos. A fim de obter essa exploração, nosso trabalho anterior propôs um novo operador natural discreto que resultou em bons resultados quando comparado com o C4.5 em dados do UCI. Contudo, esse operador não foi comparado com o operador natural de Aguilar-Ruiz et al. Assim, neste trabalho, nós apresentamos essa comparação e definimos um novo operador natural contínuo o qual é também avaliado. Resultados mostram que nossos operadores obtêm melhor precisão e conceitos mais simples usando menos tempo.Referências
Aguilar-Ruiz Jesús S. , Riquelme J.C. e Carmelo D. V. “Improving the Evolutionary Coding for Machine Learning Tasks”. European Conference on Artificial Intelligence, IOS Press, Lyon, France 2002, pp 173-177
Aguilar–Ruiz Jesús. S., Riquelme J. C. e Toro M.. “Evolutionary Learning of Hierarchical Decision Rules.” IEEE Transactions on Systems, Man e Cybernetics, Part B, 33(2), 2003, pp. 324–331.
Bacardit, J. e Butz, M.V., “Data Mining in Learning Classifier Systems: Comparing XCS with GAssist”, 7th Inter. Workshop on Learning Classifier Systems, Springer-Verlag, Seattle, USA, 2004, pp. 381-387.
Blake, C.L. e Merz, C.J., “UCI Repository of machine learning databases”, Irvine, CA: University of California, Department of Information e Computer Science, 1998, [link]
DeJong, K. A. e Spears, W. M. 1991. “Learning Concept Classification Rules Using Genetic Algorithms.” 12th International Joint Conference on Artificial Intelligence, Morgan Kaufmann., Sydney, Australia, 1991., pp. 51-56.
DeJong K. A, W. M. Spears, e D. F. Gordon, "Using genetic algorithms for concept learning," Machine. Learning, vol. 1, no. 13, 1993, pp. 161-188.
Eiben A.E. e Schippers A., “On Evolutionary Exploration e Exploitation”. Fundamenta Informaticae, IOS Press, Amsterdam, The Netherles, Vol. 35, Issue 1-4, 1998, pp. 35-50
Fayyad U. M. e Irani K. B.. “Multi-interval discretization of continuous valued attributes for classification learning”, Proceedings of the 13th International Joint Conference on Artificial Intelligence, Morgan Kaufmann, Chambery, France, 1993, pp. 1022-1027.
Goldberg., David. E., Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, Reading, Massachusetts, 1989.
Pitangui, C., Zaverucha, G. “Genetic Based Machine Learning: Merging Pittsburgh and Michigan, an Implicit Feature Selection Mechanism e a New Crossover Operator”. 6th International Conference on Hybrid Intelligent Systems. Auckland, New Zealand, 2006.
Quinlan J. R. C4.5: Programs for Machine Learning. Morgan Kaufmann, San Francisco, 1993.
Witten Ian H. e Frank Eibe (2005) Data Mining: Practical machine learning tools and techniques, 2nd Edition, Morgan Kaufmann, San Francisco, 2005.
Aguilar–Ruiz Jesús. S., Riquelme J. C. e Toro M.. “Evolutionary Learning of Hierarchical Decision Rules.” IEEE Transactions on Systems, Man e Cybernetics, Part B, 33(2), 2003, pp. 324–331.
Bacardit, J. e Butz, M.V., “Data Mining in Learning Classifier Systems: Comparing XCS with GAssist”, 7th Inter. Workshop on Learning Classifier Systems, Springer-Verlag, Seattle, USA, 2004, pp. 381-387.
Blake, C.L. e Merz, C.J., “UCI Repository of machine learning databases”, Irvine, CA: University of California, Department of Information e Computer Science, 1998, [link]
DeJong, K. A. e Spears, W. M. 1991. “Learning Concept Classification Rules Using Genetic Algorithms.” 12th International Joint Conference on Artificial Intelligence, Morgan Kaufmann., Sydney, Australia, 1991., pp. 51-56.
DeJong K. A, W. M. Spears, e D. F. Gordon, "Using genetic algorithms for concept learning," Machine. Learning, vol. 1, no. 13, 1993, pp. 161-188.
Eiben A.E. e Schippers A., “On Evolutionary Exploration e Exploitation”. Fundamenta Informaticae, IOS Press, Amsterdam, The Netherles, Vol. 35, Issue 1-4, 1998, pp. 35-50
Fayyad U. M. e Irani K. B.. “Multi-interval discretization of continuous valued attributes for classification learning”, Proceedings of the 13th International Joint Conference on Artificial Intelligence, Morgan Kaufmann, Chambery, France, 1993, pp. 1022-1027.
Goldberg., David. E., Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, Reading, Massachusetts, 1989.
Pitangui, C., Zaverucha, G. “Genetic Based Machine Learning: Merging Pittsburgh and Michigan, an Implicit Feature Selection Mechanism e a New Crossover Operator”. 6th International Conference on Hybrid Intelligent Systems. Auckland, New Zealand, 2006.
Quinlan J. R. C4.5: Programs for Machine Learning. Morgan Kaufmann, San Francisco, 1993.
Witten Ian H. e Frank Eibe (2005) Data Mining: Practical machine learning tools and techniques, 2nd Edition, Morgan Kaufmann, San Francisco, 2005.
Publicado
30/06/2007
Como Citar
PITANGUI, Cristiano; ZAVERUCHA, Gerson.
Aprendizado Genético: Operadores de Crossover Naturais Aprimorados. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 6. , 2007, Rio de Janeiro/RJ.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2007
.
p. 1222-1231.
ISSN 2763-9061.
