Implementing spike-timing-dependent plasticity on SpiNNaker neuromorphic hardware

Xin Jin; Alexander Rast; Francesco Galluppi; Sergio Davies; Steve Furber

doi:10.1109/IJCNN.2010.5596372

Implementing spike-timing-dependent plasticity on SpiNNaker neuromorphic hardware

Xin Jin, Alexander Rast, Francesco Galluppi, Sergio Davies, Steve Furber

Advanced Processor Technology

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

Abstract

This paper presents an efficient approach for implementing spike-timing-dependent plasticity (STDP) on the SpiNNaker neuromorphic hardware. The event-address mapping and the distributed synaptic weight storage schemes used in parallel neuromorphic hardware such as SpiNNaker make the conventional pre-post-sensitive scheme of STDP implementation inefficient, since STDP is triggered when either a pre- or post-synaptic neuron fires. An alternative pre-sensitive scheme approach is presented to solve this problem, where STDP is triggered only when a pre-synaptic neuron fires. An associated deferred event-driven model is developed to enable the pre-sensitive scheme by deferring the STDP process until there are sufficient history spike timing records. The paper gives detailed description of the implementation as well as performance estimation of STDP on multi-chip SpiNNaker machine, along with the discussion on some issues related to efficient STDP implementation on a parallel neuromorphic hardware. © 2010 IEEE.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks\|Proc Int Jt Conf Neural Networks
Place of Publication	USA
Publisher	IEEE
ISBN (Print)	9781424469178
DOIs	https://doi.org/10.1109/IJCNN.2010.5596372
Publication status	Published - 2010
Event	2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010 - Barcelona Duration: 1 Jul 2010 → …

Conference

Conference	2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010
City	Barcelona
Period	1/07/10 → …

Keywords

brain models , neural nets

Access to Document

10.1109/IJCNN.2010.5596372

Cite this

@inproceedings{52d1d8e6a2c640e5bb7be40ae3a48720,

title = "Implementing spike-timing-dependent plasticity on SpiNNaker neuromorphic hardware",

abstract = "This paper presents an efficient approach for implementing spike-timing-dependent plasticity (STDP) on the SpiNNaker neuromorphic hardware. The event-address mapping and the distributed synaptic weight storage schemes used in parallel neuromorphic hardware such as SpiNNaker make the conventional pre-post-sensitive scheme of STDP implementation inefficient, since STDP is triggered when either a pre- or post-synaptic neuron fires. An alternative pre-sensitive scheme approach is presented to solve this problem, where STDP is triggered only when a pre-synaptic neuron fires. An associated deferred event-driven model is developed to enable the pre-sensitive scheme by deferring the STDP process until there are sufficient history spike timing records. The paper gives detailed description of the implementation as well as performance estimation of STDP on multi-chip SpiNNaker machine, along with the discussion on some issues related to efficient STDP implementation on a parallel neuromorphic hardware. {\textcopyright} 2010 IEEE.",

keywords = "brain models , neural nets",

author = "Xin Jin and Alexander Rast and Francesco Galluppi and Sergio Davies and Steve Furber",

year = "2010",

doi = "10.1109/IJCNN.2010.5596372",

language = "English",

isbn = "9781424469178",

booktitle = "Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks",

publisher = "IEEE",

address = "United States",

note = "2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010 ; Conference date: 01-07-2010",

}

Jin, X, Rast, A, Galluppi, F, Davies, S & Furber, S 2010, Implementing spike-timing-dependent plasticity on SpiNNaker neuromorphic hardware. in Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks. IEEE, USA, 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010, Barcelona, 1/07/10. https://doi.org/10.1109/IJCNN.2010.5596372

TY - GEN

T1 - Implementing spike-timing-dependent plasticity on SpiNNaker neuromorphic hardware

AU - Jin, Xin

AU - Rast, Alexander

AU - Galluppi, Francesco

AU - Davies, Sergio

AU - Furber, Steve

PY - 2010

Y1 - 2010

N2 - This paper presents an efficient approach for implementing spike-timing-dependent plasticity (STDP) on the SpiNNaker neuromorphic hardware. The event-address mapping and the distributed synaptic weight storage schemes used in parallel neuromorphic hardware such as SpiNNaker make the conventional pre-post-sensitive scheme of STDP implementation inefficient, since STDP is triggered when either a pre- or post-synaptic neuron fires. An alternative pre-sensitive scheme approach is presented to solve this problem, where STDP is triggered only when a pre-synaptic neuron fires. An associated deferred event-driven model is developed to enable the pre-sensitive scheme by deferring the STDP process until there are sufficient history spike timing records. The paper gives detailed description of the implementation as well as performance estimation of STDP on multi-chip SpiNNaker machine, along with the discussion on some issues related to efficient STDP implementation on a parallel neuromorphic hardware. © 2010 IEEE.

AB - This paper presents an efficient approach for implementing spike-timing-dependent plasticity (STDP) on the SpiNNaker neuromorphic hardware. The event-address mapping and the distributed synaptic weight storage schemes used in parallel neuromorphic hardware such as SpiNNaker make the conventional pre-post-sensitive scheme of STDP implementation inefficient, since STDP is triggered when either a pre- or post-synaptic neuron fires. An alternative pre-sensitive scheme approach is presented to solve this problem, where STDP is triggered only when a pre-synaptic neuron fires. An associated deferred event-driven model is developed to enable the pre-sensitive scheme by deferring the STDP process until there are sufficient history spike timing records. The paper gives detailed description of the implementation as well as performance estimation of STDP on multi-chip SpiNNaker machine, along with the discussion on some issues related to efficient STDP implementation on a parallel neuromorphic hardware. © 2010 IEEE.

KW - brain models , neural nets

U2 - 10.1109/IJCNN.2010.5596372

DO - 10.1109/IJCNN.2010.5596372

M3 - Conference contribution

SN - 9781424469178

BT - Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks

PB - IEEE

CY - USA

T2 - 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010

Y2 - 1 July 2010

ER -

Implementing spike-timing-dependent plasticity on SpiNNaker neuromorphic hardware

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this