Deterministic Boltzmann Machine Learning Improved for Analog LSI Implementation

Takashi MORIE  Yoshihito AMEMIYA  

Publication
IEICE TRANSACTIONS on Electronics   Vol.E76-C   No.7   pp.1167-1173
Publication Date: 1993/07/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (Special Issue on New Architecture LSIs)
Category: Neural Networks and Chips
Keyword: 
neural network,  Boltzmann machine,  analog LSI,  mean-field theory learning,  

Full Text: PDF(591KB)>>
Buy this Article



Summary: 
This paper describes the learning performance of the deterministic Boltzmann machine (DBM), which is a promising neural network model suitable for analog LSI implementation. (i) A new learning procedure suitable for LSI implementation is proposed. This is fully-on-line learning in which different sample patterns are presented in consecutive clamped and free phases and the weights are modified in each phase. This procedure is implemented without extra memories for learning operation, and reduces the chip area and power consumption for learning by 50 percent. (ii) Learning in a layer-type DBM with one output unit has characteristic local minima which reduce the effective number of available hidden units. Effective methods to avoid reaching these local minima are proposed. (iii) Although DBM learning is not suitable for mapping problems with analog target values, it is useful for analog data discrimination problems.