Finding Optimal Architectures and Weights for ANN: A Combined Hierarchical Approach

摘要

In this paper, we present a novel approach of implementing a combined hierarchical methodology to find appropriate neural network architecture and weights using an evolutionary least square based algorithm (GALS). This paper focuses on the aspects such as the heuristics of updating weights using an evolutionary least square based algorithm, finding the number of hidden neurons for a two layer feed forward neural network, the stopping criteria for the algorithm and finally comparisons of the results with error back propagation (EBP) algorithm.