Real-time event-driven spiking neural network object recognition on the SpiNNaker platform

Garrick Orchard; Xavier Lagorce; Christoph Posch; Stephen Furber; Ryad Benosman; Francesco Galluppi

doi:10.1109/ISCAS.2015.7169171

Real-time event-driven spiking neural network object recognition on the SpiNNaker platform

Garrick Orchard, Xavier Lagorce, Christoph Posch, Stephen Furber, Ryad Benosman, Francesco Galluppi

Advanced Processor Technology

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

Abstract

This paper presents a real-time spiking neural network adaptation of the HMAX object recognition model on an event-driven platform. Visual input is provided by a spiking silicon retina, while the SpiNNaker system is used as a computational hardware platform for implementation. We show the implementation of a simple Leaky Integrate-and-Fire (LIF) neuron model on SpiNNaker to create an event driven network, where a neuron only updates when it receives an interrupt indicating that a new input spike has been received. The model output consists of view tuned neurons which respond selectively to a particular view of an object. The network can be used to discriminate between objects, or between the same object at different views. On a 26 class character recognition task, the correct class is always assigned the highest probability (69.42% on average).

Original language	English
Title of host publication	Proceedings - IEEE International Symposium on Circuits and Systems
Publisher	IEEE
Pages	2413-2416
Number of pages	4
Volume	2015-July
ISBN (Print)	9781479983919
DOIs	https://doi.org/10.1109/ISCAS.2015.7169171
Publication status	Published - 27 Jul 2015
Event	IEEE International Symposium on Circuits and Systems, ISCAS 2015 - Lisbon, Portugal Duration: 24 May 2015 → 27 May 2015 http://www.scopus.com/inward/record.url?eid=2-s2.0-84946225388&partnerID=40&md5=58467212fe9944b83fe45c3ea4058d6b

Conference

Conference	IEEE International Symposium on Circuits and Systems, ISCAS 2015
Country/Territory	Portugal
City	Lisbon
Period	24/05/15 → 27/05/15
Internet address	http://www.scopus.com/inward/record.url?eid=2-s2.0-84946225388&partnerID=40&md5=58467212fe9944b83fe45c3ea4058d6b

Access to Document

10.1109/ISCAS.2015.7169171

Cite this

@inproceedings{2787a546f07e4f128806bed14b1a1bce,

title = "Real-time event-driven spiking neural network object recognition on the SpiNNaker platform",

abstract = "This paper presents a real-time spiking neural network adaptation of the HMAX object recognition model on an event-driven platform. Visual input is provided by a spiking silicon retina, while the SpiNNaker system is used as a computational hardware platform for implementation. We show the implementation of a simple Leaky Integrate-and-Fire (LIF) neuron model on SpiNNaker to create an event driven network, where a neuron only updates when it receives an interrupt indicating that a new input spike has been received. The model output consists of view tuned neurons which respond selectively to a particular view of an object. The network can be used to discriminate between objects, or between the same object at different views. On a 26 class character recognition task, the correct class is always assigned the highest probability (69.42% on average).",

author = "Garrick Orchard and Xavier Lagorce and Christoph Posch and Stephen Furber and Ryad Benosman and Francesco Galluppi",

year = "2015",

month = jul,

day = "27",

doi = "10.1109/ISCAS.2015.7169171",

language = "English",

isbn = "9781479983919",

volume = "2015-July",

pages = "2413--2416",

booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",

publisher = "IEEE",

address = "United States",

note = "IEEE International Symposium on Circuits and Systems, ISCAS 2015 ; Conference date: 24-05-2015 Through 27-05-2015",

url = "http://www.scopus.com/inward/record.url?eid=2-s2.0-84946225388&partnerID=40&md5=58467212fe9944b83fe45c3ea4058d6b",

}

Orchard, G, Lagorce, X, Posch, C, Furber, S, Benosman, R & Galluppi, F 2015, Real-time event-driven spiking neural network object recognition on the SpiNNaker platform. in Proceedings - IEEE International Symposium on Circuits and Systems. vol. 2015-July, 7169171, IEEE, pp. 2413-2416, IEEE International Symposium on Circuits and Systems, ISCAS 2015, Lisbon, Portugal, 24/05/15. https://doi.org/10.1109/ISCAS.2015.7169171

Real-time event-driven spiking neural network object recognition on the SpiNNaker platform. / Orchard, Garrick; Lagorce, Xavier; Posch, Christoph et al.
Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 2015-July IEEE, 2015. p. 2413-2416 7169171.

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

TY - GEN

T1 - Real-time event-driven spiking neural network object recognition on the SpiNNaker platform

AU - Orchard, Garrick

AU - Lagorce, Xavier

AU - Posch, Christoph

AU - Furber, Stephen

AU - Benosman, Ryad

AU - Galluppi, Francesco

PY - 2015/7/27

Y1 - 2015/7/27

N2 - This paper presents a real-time spiking neural network adaptation of the HMAX object recognition model on an event-driven platform. Visual input is provided by a spiking silicon retina, while the SpiNNaker system is used as a computational hardware platform for implementation. We show the implementation of a simple Leaky Integrate-and-Fire (LIF) neuron model on SpiNNaker to create an event driven network, where a neuron only updates when it receives an interrupt indicating that a new input spike has been received. The model output consists of view tuned neurons which respond selectively to a particular view of an object. The network can be used to discriminate between objects, or between the same object at different views. On a 26 class character recognition task, the correct class is always assigned the highest probability (69.42% on average).

AB - This paper presents a real-time spiking neural network adaptation of the HMAX object recognition model on an event-driven platform. Visual input is provided by a spiking silicon retina, while the SpiNNaker system is used as a computational hardware platform for implementation. We show the implementation of a simple Leaky Integrate-and-Fire (LIF) neuron model on SpiNNaker to create an event driven network, where a neuron only updates when it receives an interrupt indicating that a new input spike has been received. The model output consists of view tuned neurons which respond selectively to a particular view of an object. The network can be used to discriminate between objects, or between the same object at different views. On a 26 class character recognition task, the correct class is always assigned the highest probability (69.42% on average).

UR - http://www.scopus.com/inward/record.url?scp=84946220655&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2015.7169171

DO - 10.1109/ISCAS.2015.7169171

M3 - Conference contribution

AN - SCOPUS:84946220655

SN - 9781479983919

VL - 2015-July

SP - 2413

EP - 2416

BT - Proceedings - IEEE International Symposium on Circuits and Systems

PB - IEEE

T2 - IEEE International Symposium on Circuits and Systems, ISCAS 2015

Y2 - 24 May 2015 through 27 May 2015

ER -

Real-time event-driven spiking neural network object recognition on the SpiNNaker platform

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this