Probabilistic inference using stochastic spiking neural networks on a neurosynaptic processor

Khadeer Ahmed, Amar Shrestha, Qinru Qiu, Qing Wu

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

4 Citations (Scopus)

Abstract

Spiking neural networks are rapidly gaining popularity for their ability to perform efficient computation akin to the way a brain processes information. It has the potential to achieve low cost and high energy efficiency due to the distributed nature of neural computation and the use of low energy spikes for information exchange. A stochastic spiking neural network naturally can be used to realize Bayesian inference. IBM's TrueNorth is a neurosynaptic processor that has more than 1 million digital spiking neurons and 268 million digital synapses with less than 200 mW peak power. In this paper we propose the first work that converts an inference network to a spiking neural network that runs on the TrueNorth processor. Using inference-based sentence construction as a case study, we discuss algorithms that transform an inference network to a spiking neural network, and a spiking neural network to TrueNorth corelet designs. In our experiments, the TrueNorth spiking neural network constructed sentences have a matching accuracy of 88% while consuming an average power of 0.205 mW.

Original languageEnglish (US)
Title of host publication2016 International Joint Conference on Neural Networks, IJCNN 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4286-4293
Number of pages8
Volume2016-October
ISBN (Electronic)9781509006199
DOIs
StatePublished - Oct 31 2016
Event2016 International Joint Conference on Neural Networks, IJCNN 2016 - Vancouver, Canada
Duration: Jul 24 2016Jul 29 2016

Other

Other2016 International Joint Conference on Neural Networks, IJCNN 2016
CountryCanada
CityVancouver
Period7/24/167/29/16

Fingerprint

Neural networks
Neurons
Energy efficiency
Brain
Costs
Experiments

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Ahmed, K., Shrestha, A., Qiu, Q., & Wu, Q. (2016). Probabilistic inference using stochastic spiking neural networks on a neurosynaptic processor. In 2016 International Joint Conference on Neural Networks, IJCNN 2016 (Vol. 2016-October, pp. 4286-4293). [7727759] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2016.7727759

Probabilistic inference using stochastic spiking neural networks on a neurosynaptic processor. / Ahmed, Khadeer; Shrestha, Amar; Qiu, Qinru; Wu, Qing.

2016 International Joint Conference on Neural Networks, IJCNN 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. p. 4286-4293 7727759.

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

Ahmed, K, Shrestha, A, Qiu, Q & Wu, Q 2016, Probabilistic inference using stochastic spiking neural networks on a neurosynaptic processor. in 2016 International Joint Conference on Neural Networks, IJCNN 2016. vol. 2016-October, 7727759, Institute of Electrical and Electronics Engineers Inc., pp. 4286-4293, 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, Canada, 7/24/16. https://doi.org/10.1109/IJCNN.2016.7727759
Ahmed K, Shrestha A, Qiu Q, Wu Q. Probabilistic inference using stochastic spiking neural networks on a neurosynaptic processor. In 2016 International Joint Conference on Neural Networks, IJCNN 2016. Vol. 2016-October. Institute of Electrical and Electronics Engineers Inc. 2016. p. 4286-4293. 7727759 https://doi.org/10.1109/IJCNN.2016.7727759
Ahmed, Khadeer ; Shrestha, Amar ; Qiu, Qinru ; Wu, Qing. / Probabilistic inference using stochastic spiking neural networks on a neurosynaptic processor. 2016 International Joint Conference on Neural Networks, IJCNN 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. pp. 4286-4293
@inproceedings{2978f4a13e6d4b7e937dc3f99056a91f,
title = "Probabilistic inference using stochastic spiking neural networks on a neurosynaptic processor",
abstract = "Spiking neural networks are rapidly gaining popularity for their ability to perform efficient computation akin to the way a brain processes information. It has the potential to achieve low cost and high energy efficiency due to the distributed nature of neural computation and the use of low energy spikes for information exchange. A stochastic spiking neural network naturally can be used to realize Bayesian inference. IBM's TrueNorth is a neurosynaptic processor that has more than 1 million digital spiking neurons and 268 million digital synapses with less than 200 mW peak power. In this paper we propose the first work that converts an inference network to a spiking neural network that runs on the TrueNorth processor. Using inference-based sentence construction as a case study, we discuss algorithms that transform an inference network to a spiking neural network, and a spiking neural network to TrueNorth corelet designs. In our experiments, the TrueNorth spiking neural network constructed sentences have a matching accuracy of 88{\%} while consuming an average power of 0.205 mW.",
author = "Khadeer Ahmed and Amar Shrestha and Qinru Qiu and Qing Wu",
year = "2016",
month = "10",
day = "31",
doi = "10.1109/IJCNN.2016.7727759",
language = "English (US)",
volume = "2016-October",
pages = "4286--4293",
booktitle = "2016 International Joint Conference on Neural Networks, IJCNN 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Probabilistic inference using stochastic spiking neural networks on a neurosynaptic processor

AU - Ahmed, Khadeer

AU - Shrestha, Amar

AU - Qiu, Qinru

AU - Wu, Qing

PY - 2016/10/31

Y1 - 2016/10/31

N2 - Spiking neural networks are rapidly gaining popularity for their ability to perform efficient computation akin to the way a brain processes information. It has the potential to achieve low cost and high energy efficiency due to the distributed nature of neural computation and the use of low energy spikes for information exchange. A stochastic spiking neural network naturally can be used to realize Bayesian inference. IBM's TrueNorth is a neurosynaptic processor that has more than 1 million digital spiking neurons and 268 million digital synapses with less than 200 mW peak power. In this paper we propose the first work that converts an inference network to a spiking neural network that runs on the TrueNorth processor. Using inference-based sentence construction as a case study, we discuss algorithms that transform an inference network to a spiking neural network, and a spiking neural network to TrueNorth corelet designs. In our experiments, the TrueNorth spiking neural network constructed sentences have a matching accuracy of 88% while consuming an average power of 0.205 mW.

AB - Spiking neural networks are rapidly gaining popularity for their ability to perform efficient computation akin to the way a brain processes information. It has the potential to achieve low cost and high energy efficiency due to the distributed nature of neural computation and the use of low energy spikes for information exchange. A stochastic spiking neural network naturally can be used to realize Bayesian inference. IBM's TrueNorth is a neurosynaptic processor that has more than 1 million digital spiking neurons and 268 million digital synapses with less than 200 mW peak power. In this paper we propose the first work that converts an inference network to a spiking neural network that runs on the TrueNorth processor. Using inference-based sentence construction as a case study, we discuss algorithms that transform an inference network to a spiking neural network, and a spiking neural network to TrueNorth corelet designs. In our experiments, the TrueNorth spiking neural network constructed sentences have a matching accuracy of 88% while consuming an average power of 0.205 mW.

UR - http://www.scopus.com/inward/record.url?scp=85007275319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007275319&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2016.7727759

DO - 10.1109/IJCNN.2016.7727759

M3 - Conference contribution

AN - SCOPUS:85007275319

VL - 2016-October

SP - 4286

EP - 4293

BT - 2016 International Joint Conference on Neural Networks, IJCNN 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -