%P 2510-2513
%A N.H. Hamid
%A A.F. Murray
%A D. Laurenson
%A S. Roy
%A B. Cheng
%T Probabilistic computing with future deep sub-micrometer devices : A modelling approach
%C Kobe
%L scholars2
%J Proceedings - IEEE International Symposium on Circuits and Systems
%O cited By 3; Conference of IEEE International Symposium on Circuits and Systems 2005, ISCAS 2005 ; Conference Date: 23 May 2005 Through 26 May 2005; Conference Code:77312
%R 10.1109/ISCAS.2005.1465136
%D 2005
%X An approach is described that investigates the potential of probabilistic "neural" architectures for computation with Deep Sub-Micrometer (DSM) MOSFETs. Initially, noisy MOSFET models are based upon those for a 0.35μm MOS technology with an exaggerated 1/f characteristic. We explore the manifestation of the 1/f characteristic at the output of 2-quadrant multiplier when the key n-channel MOSFETs are replaced by "noisy" MOSFETs. The stochastic behavior of this noisy multiplier has been mapped on to a software (Matlab) model of a Continuous Restricted Boltzmann Machine (CRBM) - an analogue-input stochastic computing structure. Simulation of this DSM CRBM implementation shows little degradation from that of a "perfect" CRBM. This paper thus introduces a methodology for a form of "technology-downstreaming" and highlights the potential of probabilistic architectures for DSM computation. © 2005 IEEE.
%K MOS technology; Mosfet model; MOSFETs; N-channel; Probabilistic computing; Restricted boltzmann machine; Stochastic behavior; Submicrometer, Electric load management; Frequency multiplying circuits; MATLAB; Micrometers; MOSFET devices; Random processes, Stochastic models