Efficient learning of NN-MLP based on individual evolutionary algorithm

Qiangfu Zhao

doi:10.1016/0925-2312(95)00088-7

Efficient learning of NN-MLP based on individual evolutionary algorithm

1996-10-01

5

PRE

AI

DOI：10.1016/0925-2312(95)00088-7

Original

Original request for help

Save

Abstract

En 中文

The nearest neighbor based multilayer perceptron (NN-MLP) is a suitable model for self-organization, and has been studied by many authors in different forms. However, a large number of neurons are usually required in this kind of networks. To obtain smaller or the smallest NN-MLP, this paper introduces the concept of individual evolutionary algorithm (IEA), and proposes a new method for NN-MLP learning, There are four basic operations in the IEA: competition, gain, loss and retraining. The basic rule is: all individuals compete for surviving, winners gain more, losers lose more, and the individuals are retrained to function better than before. The learning algorithm based on the IEA is simple and suitable for parallel realization, and is able to produce the 'smallest-at-present' networks from random ones in an evolutionary manner, Its efficiency is shown by experimental results.

Keywords:

multilayer perceptron

nearest neighbor classifier

individual evolutionary algorithm

neural network learning

supervised organization

Efficient learning of NN-MLP based on individual evolutionary algorithm

Abstract

Journal

Organization