Title :
Autocompensated capacitive circuit for stochastic neural networks
Author :
Zhu, Yujia ; Belhaire, E. ; Ni, Yiyang ; Garda, Patrick
Author_Institution :
Univ. de Paris-Sud, Orsay
fDate :
2/17/1994 12:00:00 AM
Abstract :
A capacitive analogue circuit for the implementation of stochastic neural networks is described. This circuit automatically compensates for parasitic effects such as charge injection and the offset of the decision unit; it is well-suited to the implementation of the learning algorithms of Boltzmann machines
Keywords :
Boltzmann machines; CMOS integrated circuits; learning (artificial intelligence); linear integrated circuits; neural chips; switched capacitor networks; Boltzmann machines; CMOS implementation; autocompensated capacitive circuit; automatic compensation; capacitive analogue circuit; charge injection; decision unit offset; learning algorithms; parasitic effects; stochastic neural networks;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19940250
