Selection of optimal set of weights in a layered network using genetic algorithms

Abstract

Genetic algorithms represent a class of highly parallel robust adaptive search processes for solving a wide range of optimization and machine learning problems. The present work is an attempt to demonstrate their effectiveness to search a global optimal solution to select a decision boundary for a pattern recognition problem using a multilayer perceptron. The proposed method incorporates a new concept of nonlinear selection for creating mating pools and a weighted error as a fitness function. Since there is no need for the backpropagation technique, the algorithm is computationally efficient and avoids all the drawbacks of the backpropagation algorithm. Moreover, it does not depend on the sequence of the training data. The performance of the method along with the convergence has been experimentally demonstrated for both linearly separable and nonseparable pattern classes.