EVOLUTIONARY ALGORITHM FOR TRAINING COMPACT SINGLE HIDDEN LAYER FEEDFORWARD NEURAL NETWORKS

Advanced Artificial Intelligence

EVOLUTIONARY ALGORITHM FOR TRAINING

COMPACT SINGLE HIDDEN LAYER

FEEDFORWARD NEURAL NETWORKS

HIEU TRUNG HUYNH AND YONGGWAN WON, MEMBER, IEEE

Group members:

Mr. Nhan

Mr. Dien.Vo

Mr. Tu

IUH University

ABSTRACT

An effective training algorithm called extreme learning machine (ELM) has recently proposed for

single hidden layer feedforward neural networks (SLFNs).

It randomly chooses the input weights and hidden layer biases, and analytically determines the

output weights by a simple matrix-inversion operation.

This algorithm can achieve good performance at extremely high learning speed. However, it may

require a large number of hidden units due to non-optimal input weights and hidden layer biases.

In this paper, group of authors propose a new approach, evolutionary least-squares extreme

learning machine (ELS-ELM), to determine the input weights and biases of hidden units using

the differential evolution algorithm in which the initial generation is generated not by random

selection but by a least squares scheme.

Experimental results for function approximation show that this approach can obtain good

generalization performance with compact networks.

IUH University