Simulation of Bayesian learning and inference on distributed stochastic spiking neural networks

Khadeer Ahmed, Amar Shrestha, Qinru Qiu

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

3 Citations (Scopus)

Abstract

The ability of neural networks to perform pattern recognition, classification and associative memory, is essential to applications such as image and speech recognition, natural language understanding, decision making etc. In spiking neural networks (SNNs), information is encoded as sparsely distributed train of spikes, which allows learning through the spike-timing dependent plasticity (STDP) property. SNNs can potentially achieve very large scale implementation and distributed learning due to the inherent asynchronous and sparse inter-neuron communications. In this work, we develop an efficient, scalable and flexible SNN simulator, which supports learning through STDP. The simulator is ideal for biologically inspired neuron models for computation but not for biologically realistic models. Bayesian neuron model for SNNs that is capable of online and fully-distributed STDP learning is introduced. The function of the simulator is validated using two networks representing two different applications from unsupervised feature extraction to inference based sentence construction.

Original languageEnglish (US)
Title of host publication2016 International Joint Conference on Neural Networks, IJCNN 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1044-1051
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
Plasticity
Simulators
Image recognition
Speech recognition
Pattern recognition
Feature extraction
Decision making
Data storage equipment
Communication

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Ahmed, K., Shrestha, A., & Qiu, Q. (2016). Simulation of Bayesian learning and inference on distributed stochastic spiking neural networks. In 2016 International Joint Conference on Neural Networks, IJCNN 2016 (Vol. 2016-October, pp. 1044-1051). [7727313] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2016.7727313

Simulation of Bayesian learning and inference on distributed stochastic spiking neural networks. / Ahmed, Khadeer; Shrestha, Amar; Qiu, Qinru.

2016 International Joint Conference on Neural Networks, IJCNN 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. p. 1044-1051 7727313.

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

Ahmed, K, Shrestha, A & Qiu, Q 2016, Simulation of Bayesian learning and inference on distributed stochastic spiking neural networks. in 2016 International Joint Conference on Neural Networks, IJCNN 2016. vol. 2016-October, 7727313, Institute of Electrical and Electronics Engineers Inc., pp. 1044-1051, 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, Canada, 7/24/16. https://doi.org/10.1109/IJCNN.2016.7727313
Ahmed K, Shrestha A, Qiu Q. Simulation of Bayesian learning and inference on distributed stochastic spiking neural networks. In 2016 International Joint Conference on Neural Networks, IJCNN 2016. Vol. 2016-October. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1044-1051. 7727313 https://doi.org/10.1109/IJCNN.2016.7727313
Ahmed, Khadeer ; Shrestha, Amar ; Qiu, Qinru. / Simulation of Bayesian learning and inference on distributed stochastic spiking neural networks. 2016 International Joint Conference on Neural Networks, IJCNN 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1044-1051
@inproceedings{912da44e41364b80aec5ae4b7272347e,
title = "Simulation of Bayesian learning and inference on distributed stochastic spiking neural networks",
abstract = "The ability of neural networks to perform pattern recognition, classification and associative memory, is essential to applications such as image and speech recognition, natural language understanding, decision making etc. In spiking neural networks (SNNs), information is encoded as sparsely distributed train of spikes, which allows learning through the spike-timing dependent plasticity (STDP) property. SNNs can potentially achieve very large scale implementation and distributed learning due to the inherent asynchronous and sparse inter-neuron communications. In this work, we develop an efficient, scalable and flexible SNN simulator, which supports learning through STDP. The simulator is ideal for biologically inspired neuron models for computation but not for biologically realistic models. Bayesian neuron model for SNNs that is capable of online and fully-distributed STDP learning is introduced. The function of the simulator is validated using two networks representing two different applications from unsupervised feature extraction to inference based sentence construction.",
author = "Khadeer Ahmed and Amar Shrestha and Qinru Qiu",
year = "2016",
month = "10",
day = "31",
doi = "10.1109/IJCNN.2016.7727313",
language = "English (US)",
volume = "2016-October",
pages = "1044--1051",
booktitle = "2016 International Joint Conference on Neural Networks, IJCNN 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Simulation of Bayesian learning and inference on distributed stochastic spiking neural networks

AU - Ahmed, Khadeer

AU - Shrestha, Amar

AU - Qiu, Qinru

PY - 2016/10/31

Y1 - 2016/10/31

N2 - The ability of neural networks to perform pattern recognition, classification and associative memory, is essential to applications such as image and speech recognition, natural language understanding, decision making etc. In spiking neural networks (SNNs), information is encoded as sparsely distributed train of spikes, which allows learning through the spike-timing dependent plasticity (STDP) property. SNNs can potentially achieve very large scale implementation and distributed learning due to the inherent asynchronous and sparse inter-neuron communications. In this work, we develop an efficient, scalable and flexible SNN simulator, which supports learning through STDP. The simulator is ideal for biologically inspired neuron models for computation but not for biologically realistic models. Bayesian neuron model for SNNs that is capable of online and fully-distributed STDP learning is introduced. The function of the simulator is validated using two networks representing two different applications from unsupervised feature extraction to inference based sentence construction.

AB - The ability of neural networks to perform pattern recognition, classification and associative memory, is essential to applications such as image and speech recognition, natural language understanding, decision making etc. In spiking neural networks (SNNs), information is encoded as sparsely distributed train of spikes, which allows learning through the spike-timing dependent plasticity (STDP) property. SNNs can potentially achieve very large scale implementation and distributed learning due to the inherent asynchronous and sparse inter-neuron communications. In this work, we develop an efficient, scalable and flexible SNN simulator, which supports learning through STDP. The simulator is ideal for biologically inspired neuron models for computation but not for biologically realistic models. Bayesian neuron model for SNNs that is capable of online and fully-distributed STDP learning is introduced. The function of the simulator is validated using two networks representing two different applications from unsupervised feature extraction to inference based sentence construction.

UR - http://www.scopus.com/inward/record.url?scp=85007154529&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007154529&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2016.7727313

DO - 10.1109/IJCNN.2016.7727313

M3 - Conference contribution

AN - SCOPUS:85007154529

VL - 2016-October

SP - 1044

EP - 1051

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

PB - Institute of Electrical and Electronics Engineers Inc.

ER -