A compact aVLSI conductance-based silicon neuron

Runchun Wang; Chetan Singh Thakur; Tara Julia Hamilton; Jonathan Tapson; André van Schaik

doi:10.1109/BioCAS.2015.7348396

A compact aVLSI conductance-based silicon neuron

Runchun Wang, Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, André van Schaik

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

12 Citations (Scopus)

Abstract

We present an analogue Very Large Scale Integration (aVLSI) implementation that uses first-order low-pass filters to implement a conductance-based silicon neuron for high-speed neuromorphic systems. The aVLSI neuron consists of a soma (cell body) and a single synapse, which is capable of linearly summing both the excitatory and inhibitory post-synaptic potentials (EPSP and IPSP) generated by the spikes arriving from different sources. Rather than biasing the silicon neuron with different parameters for different spiking patterns, as is typically done, we provide digital control signals, generated by an FPGA, to the silicon neuron to obtain different spiking behaviours. The proposed neuron is only ~26.5 Î¼m2 in the IBM 130nm process and thus can be integrated at very high density. Circuit simulations show that this neuron can emulate different spiking behaviours observed in biological neurons.

Original language	English
Title of host publication	Proceedings of the 2015 Biomedical Circuits and Systems Conference (BioCAS 2015): Engineering for Healthy Minds and Able Bodies: Atlanta, Georgia, USA, October 22-24, 2015
Publisher	IEEE
Pages	1-4
Number of pages	4
ISBN (Print)	9781479972333
DOIs	https://doi.org/10.1109/BioCAS.2015.7348396
Publication status	Published - 2015
Event	Biomedical Circuits and Systems Conference - Duration: 22 Oct 2015 → …

Conference

Conference	Biomedical Circuits and Systems Conference
Period	22/10/15 → …

Keywords

neural networks (neurobiology)
neuromorphic engineering

Access to Document

10.1109/BioCAS.2015.7348396

Cite this

@inproceedings{db380c226b044658ad8714b32cd71219,

title = "A compact aVLSI conductance-based silicon neuron",

abstract = "We present an analogue Very Large Scale Integration (aVLSI) implementation that uses first-order low-pass filters to implement a conductance-based silicon neuron for high-speed neuromorphic systems. The aVLSI neuron consists of a soma (cell body) and a single synapse, which is capable of linearly summing both the excitatory and inhibitory post-synaptic potentials (EPSP and IPSP) generated by the spikes arriving from different sources. Rather than biasing the silicon neuron with different parameters for different spiking patterns, as is typically done, we provide digital control signals, generated by an FPGA, to the silicon neuron to obtain different spiking behaviours. The proposed neuron is only ~26.5 {\^I}¼m2 in the IBM 130nm process and thus can be integrated at very high density. Circuit simulations show that this neuron can emulate different spiking behaviours observed in biological neurons.",

keywords = "neural networks (neurobiology), neuromorphic engineering",

author = "Runchun Wang and Thakur, {Chetan Singh} and Hamilton, {Tara Julia} and Jonathan Tapson and Schaik, {Andr{\'e} van}",

year = "2015",

doi = "10.1109/BioCAS.2015.7348396",

language = "English",

isbn = "9781479972333",

pages = "1--4",

booktitle = "Proceedings of the 2015 Biomedical Circuits and Systems Conference (BioCAS 2015): Engineering for Healthy Minds and Able Bodies: Atlanta, Georgia, USA, October 22-24, 2015",

publisher = "IEEE",

note = "Biomedical Circuits and Systems Conference ; Conference date: 22-10-2015",

}

Wang, R, Thakur, CS, Hamilton, TJ, Tapson, J & Schaik, AV 2015, A compact aVLSI conductance-based silicon neuron. in Proceedings of the 2015 Biomedical Circuits and Systems Conference (BioCAS 2015): Engineering for Healthy Minds and Able Bodies: Atlanta, Georgia, USA, October 22-24, 2015. IEEE, pp. 1-4, Biomedical Circuits and Systems Conference, 22/10/15. https://doi.org/10.1109/BioCAS.2015.7348396

A compact aVLSI conductance-based silicon neuron. / Wang, Runchun; Thakur, Chetan Singh; Hamilton, Tara Julia et al.
Proceedings of the 2015 Biomedical Circuits and Systems Conference (BioCAS 2015): Engineering for Healthy Minds and Able Bodies: Atlanta, Georgia, USA, October 22-24, 2015. IEEE, 2015. p. 1-4.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - A compact aVLSI conductance-based silicon neuron

AU - Wang, Runchun

AU - Thakur, Chetan Singh

AU - Hamilton, Tara Julia

AU - Tapson, Jonathan

AU - Schaik, André van

PY - 2015

Y1 - 2015

N2 - We present an analogue Very Large Scale Integration (aVLSI) implementation that uses first-order low-pass filters to implement a conductance-based silicon neuron for high-speed neuromorphic systems. The aVLSI neuron consists of a soma (cell body) and a single synapse, which is capable of linearly summing both the excitatory and inhibitory post-synaptic potentials (EPSP and IPSP) generated by the spikes arriving from different sources. Rather than biasing the silicon neuron with different parameters for different spiking patterns, as is typically done, we provide digital control signals, generated by an FPGA, to the silicon neuron to obtain different spiking behaviours. The proposed neuron is only ~26.5 Î¼m2 in the IBM 130nm process and thus can be integrated at very high density. Circuit simulations show that this neuron can emulate different spiking behaviours observed in biological neurons.

AB - We present an analogue Very Large Scale Integration (aVLSI) implementation that uses first-order low-pass filters to implement a conductance-based silicon neuron for high-speed neuromorphic systems. The aVLSI neuron consists of a soma (cell body) and a single synapse, which is capable of linearly summing both the excitatory and inhibitory post-synaptic potentials (EPSP and IPSP) generated by the spikes arriving from different sources. Rather than biasing the silicon neuron with different parameters for different spiking patterns, as is typically done, we provide digital control signals, generated by an FPGA, to the silicon neuron to obtain different spiking behaviours. The proposed neuron is only ~26.5 Î¼m2 in the IBM 130nm process and thus can be integrated at very high density. Circuit simulations show that this neuron can emulate different spiking behaviours observed in biological neurons.

KW - neural networks (neurobiology)

KW - neuromorphic engineering

UR - http://handle.uws.edu.au:8081/1959.7/uws:33910

UR - http://biocas2015.org/

U2 - 10.1109/BioCAS.2015.7348396

DO - 10.1109/BioCAS.2015.7348396

M3 - Conference Paper

SN - 9781479972333

SP - 1

EP - 4

BT - Proceedings of the 2015 Biomedical Circuits and Systems Conference (BioCAS 2015): Engineering for Healthy Minds and Able Bodies: Atlanta, Georgia, USA, October 22-24, 2015

PB - IEEE

T2 - Biomedical Circuits and Systems Conference

Y2 - 22 October 2015

ER -

A compact aVLSI conductance-based silicon neuron

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this