A Multiple Hidden Layers Extreme Learning Machine Method and Its Application

Abstract

Extreme learning machine (ELM) is a rapid learning algorithm of the single-hidden-layer feedforward neural network, which randomly initializes the weights between the input layer and the hidden layer and the bias of hidden layer neurons and finally uses the least-squares method to calculate the weights between the hidden layer and the output layer. This paper proposes a multiple hidden layers ELM (MELM for short) which inherits the characteristics of parameters of the first hidden layer. The parameters of the remaining hidden layers are obtained by introducing a method (make the actual output zero error approach the expected hidden layer output). Based on the MELM algorithm, many experiments on regression and classification show that the MELM can achieve the satisfactory results based on average precision and good generalization performance compared to the two-hidden-layer ELM (TELM), the ELM, and some other multilayer ELM.