Combinando Invenção de Predicados e Revisão de Teorias Probabilísticas de Primeira-ordem
Resumo
Durante o processo de revisão, similarmente quando aprendendo em ILP, o algoritmo pode não ser capaz de propor uma modificação útil usando a linguagem existente. Neste caso, técnicas de invenção de predicados podem ser usadas para automaticamente estender a linguagem com a definição de novos predicados. Neste trabalho, estendemos o nosso sistema de revisão de teorias probabilísticas de primeira-ordem, chamado PFORTE, com dois novos operadores de revisão que propõem novos predicados, aprendem suas definições e CPDs. Experimentos mostram que existem situações onde somos capazes de representar aspectos não observados da base de dados e conseqüentemente aprender um modelo melhor, melhorando a classificação.Referências
(1992). International union of biochemistry and molecular biology. enzyme nomenclature: recommendations (1992) of the nomenclature committee of the international union of biochemistry and molecular biology. In Academic Press, New York.
Angelopoulos, N. and Muggleton, S. (2002). Machine learning metabolic pathway descriptions using a probabilistic relational representation. Electronic Transactions in Artificial Intelligence, 6.
Beinlich, I., Suermondt, G., Chavez, R., and Cooper, G. (1989). The alarm monitorim system. In Proc. of the 2nd European Conf. on AI and Medicine.
Binder, J., Koller, D., Russell, S., and Kanazawa, K. (1997). Adaptive probabilistic networks with hidden variables. Machine Learning, 29:213–244.
Costa, V., Page, D., Qazi, M., and Cussens., J. (2003). CLP(BN): Constraint logic programming for probabilistic knowledge. In Proc. 19th UAI, pages 517–524.
Elidan, G., Lotner, N., Friedman, N., and Koller, D. (2001). Discovering hidden variables: A structure-based approach. In Advances in Neural Information Processing Systems 14, pages 479–485.
Friedman, N., Getoor, L., Koller, D., and Pfeffer, A. (1999). Learning probabilistic relational models. In Proc. 16th IJCAI, pages 1300–1309.
Kersting, K. and De Raedt, L. (2002). Basic Principles of Learning Bayesian Logic Programs. Technical Report 174, University of Freiburg.
Kok, S. and Domingos, P. (2005). Learning the structure of Markov Logic Networks. In Proc. 22nd ICML, pages 441–448.
Kramer, S. (1995). Predicate invention: A comprehensive view. Technical Report ÖFAI-TR-95-32, Austrian Research Institute for Artificial Intelligence.
Muggleton, S. (2002). Learning structure and parameters of stochastic logic programs. In Proc. 12th ILP,LNAI 2583, Springer Verlag, pages 198–206.
Paes, A., Revoredo, K., Zaverucha, G., and Costa, V. S. (2005). Probabilistic first-order theory revision from examples. In Proc. 15th ILP, LNAI 3625, Springer Verlag, pages 295–311.
Paes, A., Revoredo, K., Zaverucha, G., and Costa, V. S. (2006). PFORTE: Revising probabilistic FOL theories. In Proc. IBERAMIA-SBIA 2006, LNAI 4140, Springer Verlag, pages 441–450.
Ramachandran, S. and Mooney, R. (1998). Theory refinement of bayesian networks with hidden variables. In Proc. 15th ICML, pages 454–462.
Wrobel, S. (1996). First-order theory refinement. In Raedt, L. D., editor, Advances in Inductive Logic Programming, pages 14–33. IOS Press.
Angelopoulos, N. and Muggleton, S. (2002). Machine learning metabolic pathway descriptions using a probabilistic relational representation. Electronic Transactions in Artificial Intelligence, 6.
Beinlich, I., Suermondt, G., Chavez, R., and Cooper, G. (1989). The alarm monitorim system. In Proc. of the 2nd European Conf. on AI and Medicine.
Binder, J., Koller, D., Russell, S., and Kanazawa, K. (1997). Adaptive probabilistic networks with hidden variables. Machine Learning, 29:213–244.
Costa, V., Page, D., Qazi, M., and Cussens., J. (2003). CLP(BN): Constraint logic programming for probabilistic knowledge. In Proc. 19th UAI, pages 517–524.
Elidan, G., Lotner, N., Friedman, N., and Koller, D. (2001). Discovering hidden variables: A structure-based approach. In Advances in Neural Information Processing Systems 14, pages 479–485.
Friedman, N., Getoor, L., Koller, D., and Pfeffer, A. (1999). Learning probabilistic relational models. In Proc. 16th IJCAI, pages 1300–1309.
Kersting, K. and De Raedt, L. (2002). Basic Principles of Learning Bayesian Logic Programs. Technical Report 174, University of Freiburg.
Kok, S. and Domingos, P. (2005). Learning the structure of Markov Logic Networks. In Proc. 22nd ICML, pages 441–448.
Kramer, S. (1995). Predicate invention: A comprehensive view. Technical Report ÖFAI-TR-95-32, Austrian Research Institute for Artificial Intelligence.
Muggleton, S. (2002). Learning structure and parameters of stochastic logic programs. In Proc. 12th ILP,LNAI 2583, Springer Verlag, pages 198–206.
Paes, A., Revoredo, K., Zaverucha, G., and Costa, V. S. (2005). Probabilistic first-order theory revision from examples. In Proc. 15th ILP, LNAI 3625, Springer Verlag, pages 295–311.
Paes, A., Revoredo, K., Zaverucha, G., and Costa, V. S. (2006). PFORTE: Revising probabilistic FOL theories. In Proc. IBERAMIA-SBIA 2006, LNAI 4140, Springer Verlag, pages 441–450.
Ramachandran, S. and Mooney, R. (1998). Theory refinement of bayesian networks with hidden variables. In Proc. 15th ICML, pages 454–462.
Wrobel, S. (1996). First-order theory refinement. In Raedt, L. D., editor, Advances in Inductive Logic Programming, pages 14–33. IOS Press.
Publicado
30/06/2007
Como Citar
REVOREDO, Kate; PAES, Aline; ZAVERUCHA, Gerson; COSTA, Vitor Santos.
Combinando Invenção de Predicados e Revisão de Teorias Probabilísticas de Primeira-ordem. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 6. , 2007, Rio de Janeiro/RJ.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2007
.
p. 1351-1360.
ISSN 2763-9061.
