Actas de congresos
Evolving Gradient A New Approach To Perform Neural Network Training
Registro en:
9789896740023
Artificial Neural Networks And Intelligent Information Processing - Proc. 5th Int. Workshop On Artificial Neural Networks And Intelligent Information Processing - Anniip 2009, Held With Icinco 2009. , v. , n. , p. 3 - 12, 2009.
2-s2.0-74549132465
Autor
Berci C.D.
Bottura C.P.
Institución
Resumen
The use of genetic algorithms in ANNs training is not a new subject, several works have already accomplished good results, however not competitive with procedural methods for problems where the gradient of the error is well defined. The present document proposes an alternative for ANNs training using GA(Genetic Algorithms) to evolve the training process itself and not to evolve directly the network parameters. This way we get quite superior results and obtain a method competitive with these, usually used to training ANNs.
3 12 Battiti, R., Masulli, F., Bfgs optimization for faster and automated supervised learning (1990) INNC 90 Paris, International Neural Network Conference, pp. 757-760 Dalto Berci, C., (2008) Observadores Inteligentes de Estado: Propostas, , Tese de Mestrado, LCSI/FEEC/UNICAMP, Campinas, Brasil Dalto Berci, C., Pascoli Bottura, C., Observador inteligente adaptativo neural no baseado em modelo para sistemas no lineares (2008) Proceedings of 7th Brazilian Conference on Dynamics, Control and Applications. Présidente Prudente, 7, pp. 209-215. , Brasil Branke, J., Evolutionary algorithms for neural network design and training (1995) 1st Nordic Workshop on Genetic Algorithms and its Applications, , Vaasa, Finland, January Chalmers, D.J., The evolution of learning: An experiment in genetic connectionism (1990) Proceedings of the 1990 Connectionist Summer School, pp. 81-90 Darwin, C., (1859) On the Origin of Species by Means of Natural Selection, or the Preservation of Favoured Races in the Struggle for Life, , John Murray, London Dennett, D.C., (1995) Darwin's Dangerous Idea: Evolution and the Meanings of Life, , Penguim Books Fiszelew, A., Britos, P., Ochoa, A., Merlino, H., Fernndez, E., Garca-Martnez, R., Finding optimal neural network architecture using genetic algorithms (2004) Software & Knowledge Engineering Center. Buenos Aires Institute of Technology. Intelligent Systems Laboratory. School of Engineering. University of Buenos Aires Fyfe, C., (1996) Artificial Neural Network, , Department of Computing and Information Systems, The University of Paisley, Edition 1.1 Luenberger, D.G., (1984) Linear and Nonlinear Programming, , Addison-Wesley, 2nd edition Mller, M.F., Learning by conjugate gradients (1990) The 6th International Meeting of Young Computer Scientists Mller, M.F., A scaled conjugate gradient algorithm for fast supervised learning (1990) Computer Science Department, University of Aarhus Denmark, 6, pp. 525-533 Montana, D., Davis, L., Training feedforward neural networks using genetic algorithms (1989) Proceedings of the International Joint Conference on Artificial Intelligence, pp. 762-767 Rumelhart, D.E., Durbin, R., Golden, R., Chauvin, Y., (1995) Backpropagation: The basic theory, , Lawrence Erlbaum Associates, Inc Rumelhart, D.E., Hinton, G.E., Williams, R.J., Learning internal representations by error propagation (1986) Parallel distributed processing: Exploration in the microstructure of cognition, pp. 318-362. , Eds. D.E. Rumelhart, J.L McClelland, MIT Press, Cambridge, MA Seiffert, U., Multiple layer perceptron training using genetic algorithms (2001) ESANN'2001 proceedings - European Symposium on Artificial Neural Networks, pp. 159-164 Zhou, Z.-H., Wu, J.-X., Jiang, Y., Chen, S.-F., Genetic algorithm based selective neural network ensemble (2001) Proceedings of the 17th International Joint Conference on Artificial Intelligence, 2, pp. 797-802