ePrints

Evaluating the generalisation capability of a CMOS based synapse

Lookup NU author(s): Dr Arfan Ghani

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

The focus of this work is to investigate the generalisation capability of compact, solid-state synapses recently proposed by the authors. The synapses can be configured to yield a static or dynamic response. Empirical models of the Post Synaptic Response (PSP), derived from hardware simulations, are developed and embedded into the neural network toolbox in MATLAB. A network of these synapses was then used to solve benchmark problems using a well-established training algorithm where the performance metric was convergence time, accuracy and weight range; the Spike Response Model (SRM) was used to implement point neurons. Results are presented and compared with standard synaptic responses. (C) 2011 Elsevier B.V. All rights reserved.

Publication metadata

Author(s): Ghani A, McDaid L, Belatreche A, Hall S, Huang S, Marsland J, Dowrick T, Smith A

Publication type: Article

Publication status: Published

Journal: Neurocomputing

Year: 2012

Volume: 83

Pages: 188-197

Print publication date: 27/12/2011

ISSN (print): 0925-2312

ISSN (electronic): 1872-8286

Publisher: Elsevier BV

URL: http://dx.doi.org/10.1016/j.neucom.2011.12.010

DOI: 10.1016/j.neucom.2011.12.010

Altmetrics

Funding

Share