Artificial Neural Networks Based on Brain Circuits Behaviour and Genetic Algorithms
Abstract
Once the behaviour of particular brain circuits has been analyzed, we have added up some of these patterns to Artificial Neural Networks; thus a new hybrid learning method has emerged. In order to find the best solution to a given problem, this method combines the use of Genetic Algorithms with particular changes to connection weights based in the behaviour observed in the brain circuits analyzed. The design and implementation of this combination is shown in feed-forward multilayer artificial neural networks, specifically created to solve a simple problem. We also illustrate the benefits obtained with these new nets from a comparison with previous results achieved by the optimal Artificial Neural Networks used so far for solving the same problem.
Keywords
Genetic Algorithm Artificial Neural Network Mean Square Error Connection Weight Brain CircuitPreview
Unable to display preview. Download preview PDF.
References
- 1.Hines, M.: The NEURON simulation program. In: Skrzypek, J. (ed.) Neural Network Simulation Environments, pp. 147–163. Kluwer, Norwell (1994)Google Scholar
- 2.Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Presss, USA (1975)Google Scholar
- 3.LeRay, D., Fernández, D., Porto, A., Fuenzalida, M., Buño, W.: Heterosynaptic Metaplastic Regulation of Synaptic Efficacy in CA1 Pyramidal Neurons of Rat Hippocampus. Hippocampus (2004)Google Scholar
- 4.Porto, A.: Modelos Computacionales para optimizar el Aprendizaje y el Procesamiento de la Información en Sistemas Adaptativos: Redes Neurogliales Artificiales (RR.NG.AA.). Tesis Doctoral. Universidade da Coruña. A Coruña (2004)Google Scholar
- 5.Rabuñal, J.: Entrenamiento de Redes de Neuronas Artificiales con Algoritmos Genéticos. Tesis de Licenciatura. Dep. Computación. Facultad de Informática. Universidade da Coruña (1998)Google Scholar