Less interclass disturbance learning for unsupervised neural computing

Lurng-Kuo Liu; Panos A. Ligomenides

doi:10.1117/12.50316

1 November 1991 Less interclass disturbance learning for unsupervised neural computing

Lurng-Kuo Liu, Panos A. Ligomenides

Proceedings Volume 1606, Visual Communications and Image Processing '91: Image Processing; (1991) https://doi.org/10.1117/12.50316
Event: Visual Communications, '91, 1991, Boston, MA, United States

Abstract

A number of training algorithms for neural networks are based on the 'competition' learning method. This is regarded as an adaptive process for tuning neural networks to specific features of input. The responses from the neural network, then, tend to become localized. However, a shortcoming of this model is that some neural units can remain inactive. Since a neural unit never learns unless it wins, it is possible that some of the neural units are always outperformed by others, and therefore never learn. This paper presents a new unsupervised learning algorithm, less-interclass-disturbance learning (LID), which deals with the limitations of the simple competitive neural network. The main idea of the method is that it reinforces the competing neurons in such a way as to prevent the weights from 'fooling around.' A new compound similarity metric is introduced in this algorithm to reduce the interclass disturbance during the training process. The behavior of this algorithm was investigated through computer simulations. It is shown that LID learning is quite effective.

Citation Download Citation

Lurng-Kuo Liu and Panos A. Ligomenides "Less interclass disturbance learning for unsupervised neural computing", Proc. SPIE 1606, Visual Communications and Image Processing '91: Image Processing, (1 November 1991); https://doi.org/10.1117/12.50316

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available