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.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Takashi MORIE, Yoshihito AMEMIYA, "Deterministic Boltzmann Machine Learning Improved for Analog LSI Implementation" in IEICE TRANSACTIONS on Electronics,
vol. E76-C, no. 7, pp. 1167-1173, July 1993, doi: .
Abstract: 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.
URL: https://global.ieice.org/en_transactions/electronics/10.1587/e76-c_7_1167/_p
Copy
@ARTICLE{e76-c_7_1167,
author={Takashi MORIE, Yoshihito AMEMIYA, },
journal={IEICE TRANSACTIONS on Electronics},
title={Deterministic Boltzmann Machine Learning Improved for Analog LSI Implementation},
year={1993},
volume={E76-C},
number={7},
pages={1167-1173},
abstract={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.},
keywords={},
doi={},
ISSN={},
month={July},}
Copy
TY - JOUR
TI - Deterministic Boltzmann Machine Learning Improved for Analog LSI Implementation
T2 - IEICE TRANSACTIONS on Electronics
SP - 1167
EP - 1173
AU - Takashi MORIE
AU - Yoshihito AMEMIYA
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Electronics
SN -
VL - E76-C
IS - 7
JA - IEICE TRANSACTIONS on Electronics
Y1 - July 1993
AB - 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.
ER -