Bio-Inspired Stochastic Computing Using Binary CBRAM Synapses

 

In this paper, we present an alternative approach to neuromorphic systems based on multilevel resistive memory synapses and deterministic learning rules. We demonstrate an original methodology to use conductive-bridge RAM (CBRAM) devices as, easy to program and low-power, binary synapses with stochastic learning rules. New circuit architecture, programming strategy, and probabilistic spike-timing dependent plasticity (STDP) learning rule for two different CBRAM configurations with-selector (1T-1R) and without-selector (1R) are proposed. We show two methods (intrinsic and extrinsic) for implementing probabilistic STDP rules. Fully unsupervised learning with binary synapses is illustrated through two example applications: 1) real-time auditory pattern extraction (inspired from a 64-channel silicon cochlea emulator); and 2) visual pattern extraction (inspired from the processing inside visual cortex). High accuracy (audio pattern sensitivity ${>}{2}$, video detection rate ${>}{rm 95}%$) and low synaptic-power dissipation (audio 0.55 $mu{rm W}$, video 74.2 $mu{rm W}$) are shown. The robustness and impact of synaptic parameter variability on system performance are also analyzed.

Published in:
Electron Devices, IEEE Transactions on  (Volume:60 ,  Issue: 7 )

Date of Publication: July 2013

Cited in Nature

Our works on graphene based RTD cited (2 times) by:

 

[important]

Resonant tunnelling and negative differential conductance in graphene transistors

L. Britnell, R. V. Gorbachev, A. K. Geim, L. A. Ponomarenko, A. Mishchenko, M. T. Greenaway, T. M. Fromhold, K. S. Novoselov & L. Eaves  Nature Communications 4, Article number: 1794 doi:10.1038/ncomms2817

[/important]

 

Continue reading « Cited in Nature »

Our nanomesh in IOP top 10% !

Article, « Graphene nanomesh-based devices exhibiting a strong negative differential conductance effect », in Nanotechnology, Vol 23, pp065201 (2012), has been downloaded 250 times so far.

To put this into context, across all IOP journals 10% of articles were accessed over 250 times this quarter.

You can link directly to your article at: http://stacks.iop.org/0957-4484/23/065201

Nanotech: Graphene nanomesh and negative differential conductance

Graphene nanomesh-based devices exhibiting a strong negative differential conductance
effect

V Hung Nguyen1,2, F Mazzamuto1, J Saint-Martin1, A Bournel1 and
P Dollfus1
1 Institut d’Electronique Fondamentale, UMR8622, CNRS, Universit´e Paris Sud, 91405 Orsay, France
2 Center for Computational Physics, Institute of Physics, VAST, PO Box 429 Bo Ho, Hanoi 10000,
Vietnam
E-mail: viet-hung.nguyen@u-psud.fr
Received 21 September 2011, in final form 8 December 2011
Published 17 January 2012
Online at stacks.iop.org/Nano/23/065201

V Hung Nguyen et al 2012 Nanotechnology 23 06520

Continue reading « Nanotech: Graphene nanomesh and negative differential conductance »