Minimising Contrastive Divergence with Dynamic Current Mirrors

Authors:
Chih-Cheng Lu;H. Chen
Affiliations:
The Dept. of Electrical Engineering, The National Tsing-Hua University, Hsin-Chu, Taiwan 30013;The Dept. of Electrical Engineering, The National Tsing-Hua University, Hsin-Chu, Taiwan 30013
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Year:
2009

Citing 5
Cited 0

Learning and relearning in Boltzmann machines

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Training products of experts by minimizing contrastive divergence

Neural Computation
Kerneltron: support vector "machine" in silicon

IEEE Transactions on Neural Networks
Continuous-valued probabilistic behavior in a VLSI generative model

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Implementing probabilistic models in Very-Large-Scale-Integration (VLSI) has been attractive to implantable biomedical devices for improving sensor fusion. However, hardware non-idealities can introduce training errors, hindering optimal modelling through on-chip adaptation. This paper investigates the feasibility of using the dynamic current mirrors to implement a simple and precise training circuit. The precision required for training the Continuous Restricted Boltzmann Machine (CRBM) is first identified. A training circuit based on accumulators formed by dynamic current mirrors is then proposed. By measuring the accumulators in VLSI, the feasibility of training the CRBM on chip according to its minimizing-contrastive-divergence rule is concluded.