Um Metodo para Busca Automatica de Redes Neurais Artificiais
This work addresses the challenge of automating neural network design for researchers and practitioners, but it appears incremental as it builds on existing genetic algorithm approaches with a cellular automaton twist.
The paper tackles the problem of automatically searching for artificial neural networks by using cellular genetic algorithms to reduce local minima and simultaneously optimize weights, transfer functions, architectures, and learning rules, resulting in compact, efficient networks with shorter training times compared to other methods.
This paper describes a method that automatically searches Artificial Neural Networks using Cellular Genetic Algorithms. The main difference of this method for a common genetic algorithm is the use of a cellular automaton capable of providing the location for individuals, reducing the possibility of local minima in search space. This method employs an evolutionary search for simultaneous choices of initial weights, transfer functions, architectures and learning rules. Experimental results have shown that the developed method can find compact, efficient networks with a satisfactory generalization power and with shorter training times when compared to other methods found in the literature.