Evaluating the generalisation capability of a CMOS based synapse

Arfan Ghani, Liam McDaid, Ammar Belatreche, Stephen Hall, Shou Huang, John Marsland, Thomas Dowrick, Andy Smith

Research output: Contribution to journalArticle

3 Citations (Scopus)

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.Keywords:CMOS synapses; Spiking neural networks; CMOS implementation of spiking neurons
LanguageEnglish
Pages188-197
JournalNeurocomputing
Volume83
DOIs
Publication statusPublished - 15 Apr 2012

Fingerprint

Neurons
Neural networks
MATLAB
Dynamic response
Hardware

Keywords

  • CMOS synapses
  • Spiking neural networks
  • CMOS implementation of spiking neurons

Cite this

Ghani, A., McDaid, L., Belatreche, A., Hall, S., Huang, S., Marsland, J., ... Smith, A. (2012). Evaluating the generalisation capability of a CMOS based synapse. Neurocomputing, 83, 188-197. https://doi.org/10.1016/j.neucom.2011.12.010
Ghani, Arfan ; McDaid, Liam ; Belatreche, Ammar ; Hall, Stephen ; Huang, Shou ; Marsland, John ; Dowrick, Thomas ; Smith, Andy. / Evaluating the generalisation capability of a CMOS based synapse. In: Neurocomputing. 2012 ; Vol. 83. pp. 188-197.
@article{2d842c87431647b2862532263f4fb3d9,
title = "Evaluating the generalisation capability of a CMOS based synapse",
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.Keywords:CMOS synapses; Spiking neural networks; CMOS implementation of spiking neurons",
keywords = "CMOS synapses, Spiking neural networks, CMOS implementation of spiking neurons",
author = "Arfan Ghani and Liam McDaid and Ammar Belatreche and Stephen Hall and Shou Huang and John Marsland and Thomas Dowrick and Andy Smith",
year = "2012",
month = "4",
day = "15",
doi = "10.1016/j.neucom.2011.12.010",
language = "English",
volume = "83",
pages = "188--197",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

Ghani, A, McDaid, L, Belatreche, A, Hall, S, Huang, S, Marsland, J, Dowrick, T & Smith, A 2012, 'Evaluating the generalisation capability of a CMOS based synapse', Neurocomputing, vol. 83, pp. 188-197. https://doi.org/10.1016/j.neucom.2011.12.010

Evaluating the generalisation capability of a CMOS based synapse. / Ghani, Arfan; McDaid, Liam; Belatreche, Ammar; Hall, Stephen; Huang, Shou; Marsland, John; Dowrick, Thomas; Smith, Andy.

In: Neurocomputing, Vol. 83, 15.04.2012, p. 188-197.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evaluating the generalisation capability of a CMOS based synapse

AU - Ghani, Arfan

AU - McDaid, Liam

AU - Belatreche, Ammar

AU - Hall, Stephen

AU - Huang, Shou

AU - Marsland, John

AU - Dowrick, Thomas

AU - Smith, Andy

PY - 2012/4/15

Y1 - 2012/4/15

N2 - 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.Keywords:CMOS synapses; Spiking neural networks; CMOS implementation of spiking neurons

AB - 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.Keywords:CMOS synapses; Spiking neural networks; CMOS implementation of spiking neurons

KW - CMOS synapses

KW - Spiking neural networks

KW - CMOS implementation of spiking neurons

U2 - 10.1016/j.neucom.2011.12.010

DO - 10.1016/j.neucom.2011.12.010

M3 - Article

VL - 83

SP - 188

EP - 197

JO - Neurocomputing

T2 - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -