For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Deterministic Boltzmann Machine Learning Improved for Analog LSI Implementation
Takashi MORIE Yoshihito AMEMIYA
IEICE TRANSACTIONS on Electronics
Publication Date: 1993/07/25
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (Special Issue on New Architecture LSIs)
Category: Neural Networks and Chips
neural network, Boltzmann machine, analog LSI, mean-field theory learning,
Full Text: PDF(591KB)>>
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.