Self-Repairing Learning Rule for Spiking Astrocyte-Neuron Networks

Junxiu Liu, Liam McDaid, Jim Harkin, John Wade, Shvan Karim, Anju Johnson, Alan Millard, David Halliday, Andy Tyrrell, Jon Timmis

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

2 Citations (Scopus)

Abstract

In this paper a novel self-repairing learning rule is proposed which is a combination of the spike-timing-dependent plasticity (STDP) and Bienenstock, Cooper, and Munro (BCM) learning rules: in the derivation of this rule account is taken of the coupling of GABA interneurons to the tripartite synapse. The rule modulates the plasticity level by shifting the plasticity window, associated with STDP, up and down the vertical axis as a function of postsynaptic neural activity. Specifically when neurons are inactive, the window is shifted up the vertical axis (open) and as the postsynaptic neuron activity increases and, as learning progresses, the plasticity window moves down the vertical axis until learning ceases. Simulation results are presented which show that the proposed approach can still maintain the network performance even with a fault density approaching 80% and because the rule is implemented using a minimal computational overhead it has potential for large scale spiking neural networks in hardware.
LanguageEnglish
Title of host publicationNeural Information Processing
Subtitle of host publication24th International Conference, ICONIP 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part VI (Theoretical Computer Science and General Issues)
EditorsDerong Liu, Shengli Xie, Yuanqing Li
PublisherSpringer, Cham
Pages384-392
Number of pages9
ISBN (Electronic)9783319701363
ISBN (Print)9783319701356
DOIs
Publication statusPublished - 26 Oct 2017
Externally publishedYes
Event24th International Conference On Neural Information Processing - Guangzhou, China
Duration: 14 Nov 201718 Nov 2017
Conference number: 24
http://www.apnns.org/ICONIP2017/ (Link to Conference Website)

Conference

Conference24th International Conference On Neural Information Processing
Abbreviated titleICONIP 2017
CountryChina
CityGuangzhou
Period14/11/1718/11/17
Internet address

Fingerprint

Neurons
Plasticity
Network performance
Astrocytes
Neural networks
Hardware

Cite this

Liu, J., McDaid, L., Harkin, J., Wade, J., Karim, S., Johnson, A., ... Timmis, J. (2017). Self-Repairing Learning Rule for Spiking Astrocyte-Neuron Networks. In D. Liu, S. Xie, & Y. Li (Eds.), Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part VI (Theoretical Computer Science and General Issues) (pp. 384-392). Springer, Cham. https://doi.org/10.1007/978-3-319-70136-3_41
Liu, Junxiu ; McDaid, Liam ; Harkin, Jim ; Wade, John ; Karim, Shvan ; Johnson, Anju ; Millard, Alan ; Halliday, David ; Tyrrell, Andy ; Timmis, Jon. / Self-Repairing Learning Rule for Spiking Astrocyte-Neuron Networks. Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part VI (Theoretical Computer Science and General Issues). editor / Derong Liu ; Shengli Xie ; Yuanqing Li. Springer, Cham, 2017. pp. 384-392
@inproceedings{d82e27c0edd5446182c2c962eaf07c81,
title = "Self-Repairing Learning Rule for Spiking Astrocyte-Neuron Networks",
abstract = "In this paper a novel self-repairing learning rule is proposed which is a combination of the spike-timing-dependent plasticity (STDP) and Bienenstock, Cooper, and Munro (BCM) learning rules: in the derivation of this rule account is taken of the coupling of GABA interneurons to the tripartite synapse. The rule modulates the plasticity level by shifting the plasticity window, associated with STDP, up and down the vertical axis as a function of postsynaptic neural activity. Specifically when neurons are inactive, the window is shifted up the vertical axis (open) and as the postsynaptic neuron activity increases and, as learning progresses, the plasticity window moves down the vertical axis until learning ceases. Simulation results are presented which show that the proposed approach can still maintain the network performance even with a fault density approaching 80{\%} and because the rule is implemented using a minimal computational overhead it has potential for large scale spiking neural networks in hardware.",
author = "Junxiu Liu and Liam McDaid and Jim Harkin and John Wade and Shvan Karim and Anju Johnson and Alan Millard and David Halliday and Andy Tyrrell and Jon Timmis",
year = "2017",
month = "10",
day = "26",
doi = "10.1007/978-3-319-70136-3_41",
language = "English",
isbn = "9783319701356",
pages = "384--392",
editor = "Derong Liu and Shengli Xie and Yuanqing Li",
booktitle = "Neural Information Processing",
publisher = "Springer, Cham",

}

Liu, J, McDaid, L, Harkin, J, Wade, J, Karim, S, Johnson, A, Millard, A, Halliday, D, Tyrrell, A & Timmis, J 2017, Self-Repairing Learning Rule for Spiking Astrocyte-Neuron Networks. in D Liu, S Xie & Y Li (eds), Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part VI (Theoretical Computer Science and General Issues). Springer, Cham, pp. 384-392, 24th International Conference On Neural Information Processing, Guangzhou, China, 14/11/17. https://doi.org/10.1007/978-3-319-70136-3_41

Self-Repairing Learning Rule for Spiking Astrocyte-Neuron Networks. / Liu, Junxiu; McDaid, Liam; Harkin, Jim; Wade, John; Karim, Shvan; Johnson, Anju; Millard, Alan; Halliday, David; Tyrrell, Andy ; Timmis, Jon.

Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part VI (Theoretical Computer Science and General Issues). ed. / Derong Liu; Shengli Xie; Yuanqing Li. Springer, Cham, 2017. p. 384-392.

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

TY - GEN

T1 - Self-Repairing Learning Rule for Spiking Astrocyte-Neuron Networks

AU - Liu, Junxiu

AU - McDaid, Liam

AU - Harkin, Jim

AU - Wade, John

AU - Karim, Shvan

AU - Johnson, Anju

AU - Millard, Alan

AU - Halliday, David

AU - Tyrrell, Andy

AU - Timmis, Jon

PY - 2017/10/26

Y1 - 2017/10/26

N2 - In this paper a novel self-repairing learning rule is proposed which is a combination of the spike-timing-dependent plasticity (STDP) and Bienenstock, Cooper, and Munro (BCM) learning rules: in the derivation of this rule account is taken of the coupling of GABA interneurons to the tripartite synapse. The rule modulates the plasticity level by shifting the plasticity window, associated with STDP, up and down the vertical axis as a function of postsynaptic neural activity. Specifically when neurons are inactive, the window is shifted up the vertical axis (open) and as the postsynaptic neuron activity increases and, as learning progresses, the plasticity window moves down the vertical axis until learning ceases. Simulation results are presented which show that the proposed approach can still maintain the network performance even with a fault density approaching 80% and because the rule is implemented using a minimal computational overhead it has potential for large scale spiking neural networks in hardware.

AB - In this paper a novel self-repairing learning rule is proposed which is a combination of the spike-timing-dependent plasticity (STDP) and Bienenstock, Cooper, and Munro (BCM) learning rules: in the derivation of this rule account is taken of the coupling of GABA interneurons to the tripartite synapse. The rule modulates the plasticity level by shifting the plasticity window, associated with STDP, up and down the vertical axis as a function of postsynaptic neural activity. Specifically when neurons are inactive, the window is shifted up the vertical axis (open) and as the postsynaptic neuron activity increases and, as learning progresses, the plasticity window moves down the vertical axis until learning ceases. Simulation results are presented which show that the proposed approach can still maintain the network performance even with a fault density approaching 80% and because the rule is implemented using a minimal computational overhead it has potential for large scale spiking neural networks in hardware.

U2 - 10.1007/978-3-319-70136-3_41

DO - 10.1007/978-3-319-70136-3_41

M3 - Conference contribution

SN - 9783319701356

SP - 384

EP - 392

BT - Neural Information Processing

A2 - Liu, Derong

A2 - Xie, Shengli

A2 - Li, Yuanqing

PB - Springer, Cham

ER -

Liu J, McDaid L, Harkin J, Wade J, Karim S, Johnson A et al. Self-Repairing Learning Rule for Spiking Astrocyte-Neuron Networks. In Liu D, Xie S, Li Y, editors, Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part VI (Theoretical Computer Science and General Issues). Springer, Cham. 2017. p. 384-392 https://doi.org/10.1007/978-3-319-70136-3_41