1 November 1991 Less interclass disturbance learning for unsupervised neural computing
Author Affiliations +
Proceedings Volume 1606, Visual Communications and Image Processing '91: Image Processing; (1991); doi: 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.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lurng-Kuo Liu, 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); doi: 10.1117/12.50316; https://doi.org/10.1117/12.50316
PROCEEDINGS
12 PAGES


SHARE
KEYWORDS
Neurons

Laser induced damage

Image processing

Neural networks

Computer simulations

Visual communications

Evolutionary algorithms

RELATED CONTENT

Weighted-outer-product associative neural network
Proceedings of SPIE (November 01 1991)
Embedding domain information in backpropagation
Proceedings of SPIE (August 20 1992)
Image indexing using a texture dictionary
Proceedings of SPIE (November 21 1995)

Back to Top