Linear neural network learning algorithm analysis

Author

Yin, Hongfeng ; Klasa, Stan

Author_Institution

Dept. of Comput. Sci., Concordia Univ., Montreal, Que., Canada

Volume

5

fYear

1995

fDate

Nov/Dec 1995

Firstpage

2847

Abstract

An unsupervised perceptron algorithm and several generalizations are presented in this paper. Based on stochastic approximation theory, some general analysis of neural network learning algorithms is provided. Also, the definitions of convergence speed and robustness of a learning algorithm are given. It is shown that the unsupervised perceptron algorithms converge to the principal component of the input data under some conditions. In addition, the convergence speeds and robustness of the unsupervised perceptrons, the Oja (1982, 1983) and the Widrow-Hoff algorithms are given in explicit forms

Keywords

approximation theory; generalisation (artificial intelligence); perceptrons; unsupervised learning; convergence speed; generalizations; linear neural network learning algorithm analysis; robustness; stochastic approximation theory; unsupervised perceptron algorithm; Algorithm design and analysis; Approximation algorithms; Approximation methods; Computer science; Convergence; Difference equations; Differential equations; Neural networks; Robustness; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1995. Proceedings., IEEE International Conference on

Conference_Location

Perth, WA

Print_ISBN

0-7803-2768-3

Type

conf

DOI

10.1109/ICNN.1995.488185

Filename

488185