Self-Repairing Hardware with Astrocyte-Neuron Networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

A Self-rePAiring spiking Neural NEtwoRk(SPANNER) hardware architecture is presented in this paper. Itis based on a software model of an astrocyte-neuron networkwhich previously demonstrated the ability to self-detect faultsand self-repair autonomously. Experimental results in this papershow that when faults occur at the synapse, remaining healthysynapses of the same neuron are enhanced by the feedback fromthe astrocyte, which enables the system functionality to bemaintained. This is the first time that astrocytes cells mergedwithin spiking neurons demonstrate a self-repairing capability inhardware. This achieves a much more fine-grained repaircapability in hardware compared to the conventional faulttolerance techniques.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages1350-1353
Number of pages4
DOIs
Publication statusE-pub ahead of print - 11 Aug 2016
EventIEEE International Symposium on Circuits and Systems (ISCAS) - Canada
Duration: 11 Aug 2016 → …

Conference

ConferenceIEEE International Symposium on Circuits and Systems (ISCAS)
Period11/08/16 → …

Fingerprint

Neurons
Hardware
Repair
Neural networks
Feedback
Astrocytes

Keywords

  • Astrocyte
  • spiking neural networks
  • fault tolerance
  • FPGAs
  • repair

Cite this

@inproceedings{dcfec9335c1849088731713b7fd9197d,
title = "Self-Repairing Hardware with Astrocyte-Neuron Networks",
abstract = "A Self-rePAiring spiking Neural NEtwoRk(SPANNER) hardware architecture is presented in this paper. Itis based on a software model of an astrocyte-neuron networkwhich previously demonstrated the ability to self-detect faultsand self-repair autonomously. Experimental results in this papershow that when faults occur at the synapse, remaining healthysynapses of the same neuron are enhanced by the feedback fromthe astrocyte, which enables the system functionality to bemaintained. This is the first time that astrocytes cells mergedwithin spiking neurons demonstrate a self-repairing capability inhardware. This achieves a much more fine-grained repaircapability in hardware compared to the conventional faulttolerance techniques.",
keywords = "Astrocyte, spiking neural networks, fault tolerance, FPGAs, repair",
author = "Junxiu Liu and Jim Harkin and Liam Maguire and LJ McDaid and John Wade and W McElholm",
year = "2016",
month = "8",
day = "11",
doi = "10.1109/ISCAS.2016.7527499",
language = "English",
isbn = "978-1-4799-5340-0",
pages = "1350--1353",
booktitle = "Unknown Host Publication",

}

Liu, J, Harkin, J, Maguire, L, McDaid, LJ, Wade, J & McElholm, W 2016, Self-Repairing Hardware with Astrocyte-Neuron Networks. in Unknown Host Publication. pp. 1350-1353, IEEE International Symposium on Circuits and Systems (ISCAS), 11/08/16. https://doi.org/10.1109/ISCAS.2016.7527499

Self-Repairing Hardware with Astrocyte-Neuron Networks. / Liu, Junxiu; Harkin, Jim; Maguire, Liam; McDaid, LJ; Wade, John; McElholm, W.

Unknown Host Publication. 2016. p. 1350-1353.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Self-Repairing Hardware with Astrocyte-Neuron Networks

AU - Liu, Junxiu

AU - Harkin, Jim

AU - Maguire, Liam

AU - McDaid, LJ

AU - Wade, John

AU - McElholm, W

PY - 2016/8/11

Y1 - 2016/8/11

N2 - A Self-rePAiring spiking Neural NEtwoRk(SPANNER) hardware architecture is presented in this paper. Itis based on a software model of an astrocyte-neuron networkwhich previously demonstrated the ability to self-detect faultsand self-repair autonomously. Experimental results in this papershow that when faults occur at the synapse, remaining healthysynapses of the same neuron are enhanced by the feedback fromthe astrocyte, which enables the system functionality to bemaintained. This is the first time that astrocytes cells mergedwithin spiking neurons demonstrate a self-repairing capability inhardware. This achieves a much more fine-grained repaircapability in hardware compared to the conventional faulttolerance techniques.

AB - A Self-rePAiring spiking Neural NEtwoRk(SPANNER) hardware architecture is presented in this paper. Itis based on a software model of an astrocyte-neuron networkwhich previously demonstrated the ability to self-detect faultsand self-repair autonomously. Experimental results in this papershow that when faults occur at the synapse, remaining healthysynapses of the same neuron are enhanced by the feedback fromthe astrocyte, which enables the system functionality to bemaintained. This is the first time that astrocytes cells mergedwithin spiking neurons demonstrate a self-repairing capability inhardware. This achieves a much more fine-grained repaircapability in hardware compared to the conventional faulttolerance techniques.

KW - Astrocyte

KW - spiking neural networks

KW - fault tolerance

KW - FPGAs

KW - repair

U2 - 10.1109/ISCAS.2016.7527499

DO - 10.1109/ISCAS.2016.7527499

M3 - Conference contribution

SN - 978-1-4799-5340-0

SP - 1350

EP - 1353

BT - Unknown Host Publication

ER -