Patrice Fleury

Continuous-valued probabilistic behavior in a VLSI generative model

This paper presents the VLSI implementation of the continuous restricted Boltzmann machine (CRBM), a probabilistic generative model that is able to model continuous-valued data with a simple and hardware-amenable training algorithm. The full CRBM system consists of stochastic neurons whose continuous-valued probabilistic behavior is mediated by injected noise. Integrating on-chip training circuits, the full CRBM system provides a platform for exploring computation with continuous-valued probabilistic behavior in VLSI. The VLSI CRBMs ability both to model and to regenerate continuous-valued data distributions is examined and limitations on its performance are highlighted and discussed

On-chip contrastive divergence learning in analogue VLSI

We have mapped the contrastive divergence learning scheme of the product of experts (PoE) onto electrical circuits. The issues raised during that hardware translation are discussed in This work and some circuits presenting our solutions are described. The entire learning rule is implemented in mixed-signal VLSI on a 0.6 /spl mu/m CMOS process. Chips results validating our approach and methodology are also presented.

Unsupervised Probabilistic Neural Computation in Analogue VLSI

This chapter introduces the Continuous Restricted Boltzmann Machine, a probabilistic neural algorithm which is both useful in modelling continuous data and amenable to VLSI implementation. The capabilities of the model are explored with both artificial and real data. The computing units (neurons) and the unsupervised training rule have been implemented in VLSI. These results demonstrate the feasibility of a full VLSI model that uses continuous probabilistic behaviour to model the noise associated with all real signals, and therefore acts as a robust classifier or novelty detector.