论文信息 - Autocompensated capacitive circuit for stochastic neural networks

Autocompensated capacitive circuit for stochastic neural networks

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.

P. Garda | E. Belhaire | Y. Zhu | Y. Ni

[1] H. Matsumoto,et al. Programmable MOS charge-mode neural circuits , 1992 .

[2] Geoffrey E. Hinton,et al. A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[3] T. Yamada,et al. A self-learning neural network chip with 125 neurons and 10 K self-organization synapses , 1990, Digest of Technical Papers., 1990 Symposium on VLSI Circuits.

[4] Alan F. Murray,et al. Asynchronous VLSI neural networks using pulse-stream arithmetic , 1988 .

[5] Robert Azencott. Synchronous Boltzmann Machines and Gibbs Fields: Learning Algorithms , 1989, NATO Neurocomputing.