Um Metodo para Busca Automatica de Redes Neurais Artificiais

TL;DR

This paper introduces an automated neural network search method using cellular genetic algorithms, which efficiently finds compact, high-performing networks with reduced training times.

Contribution

It presents a novel cellular genetic algorithm approach for automatic neural network design, improving search efficiency and network quality over traditional methods.

Findings

Finds compact, efficient networks with good generalization

Reduces training times compared to existing methods

Effectively avoids local minima in search space

Abstract

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.