An elitist genetic algorithm based extreme learning machine

Abstract

Extreme Learning Machine (ELM) has been proved to be exceptionally fast and achieves more generalized performance for learning Single-hidden Layer Feedforward Neural networks (SLFN). In this paper, a Genetic Algorithm (GA) is proposed to choose the appropriate initial weights, biases and the number of hidden neurons which minimizes the classification error. The proposed GA incorporates a novel elitism approach to avoid local optimum and also speed up GA to satisfy the multi-modal function. The experimental results indicate the superior performance of the proposed algorithm with lower classification error.