Improving learning algorithm performance for spiking neural networks

Qiang Fu; Yuling Luo; Junxiu Liu; Jinjie Bi; Senhui Qiu; Yi Cao; Xuemei Ding

doi:10.1109/ICCT.2017.8359963

Improving learning algorithm performance for spiking neural networks

Qiang Fu, Yuling Luo, Junxiu Liu, Jinjie Bi, Senhui Qiu, Yi Cao, Xuemei Ding

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

Abstract / Description of output

This paper proposes three methods to improve the learning algorithm for spiking neural networks (SNNs). The aim is to improve learning performance in SNNs where neurons are allowed to fire multiple times. The performance is analyzed based on the convergence rate, the concussion condition in the training period and the error between actual output and desired output. The exclusive-or (XOR) and Wisconsin breast cancer (WBC) classification tasks are employed to validate the proposed optimized methods. Experimental results demonstrate that compared to original learning algorithm, all three methods have less iterations, higher accuracy, and more stable in the training period.

Original language	English
Title of host publication	2017 17th IEEE International Conference on Communication Technology, ICCT 2017
Publisher	Institute of Electrical and Electronics Engineers
Pages	1916-1919
Number of pages	4
ISBN (Electronic)	9781509039432
DOIs	https://doi.org/10.1109/ICCT.2017.8359963
Publication status	Published - 17 May 2018
Event	17th IEEE International Conference on Communication Technology, ICCT 2017 - Chengdu, China Duration: 27 Oct 2017 → 30 Oct 2017

Publication series

Name	International Conference on Communication Technology Proceedings, ICCT
Volume	2017-October

Conference

Conference	17th IEEE International Conference on Communication Technology, ICCT 2017
Country/Territory	China
City	Chengdu
Period	27/10/17 → 30/10/17

Keywords / Materials (for Non-textual outputs)

learning performance
optimization method
Spiking Neural Network

Access to Document

10.1109/ICCT.2017.8359963

Cite this

Fu, Q., Luo, Y., Liu, J., Bi, J., Qiu, S., Cao, Y., & Ding, X. (2018). Improving learning algorithm performance for spiking neural networks. In 2017 17th IEEE International Conference on Communication Technology, ICCT 2017 (pp. 1916-1919). (International Conference on Communication Technology Proceedings, ICCT; Vol. 2017-October). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICCT.2017.8359963

@inproceedings{54a0ff852c3e45baa58becd46f12e5e4,

title = "Improving learning algorithm performance for spiking neural networks",

abstract = "This paper proposes three methods to improve the learning algorithm for spiking neural networks (SNNs). The aim is to improve learning performance in SNNs where neurons are allowed to fire multiple times. The performance is analyzed based on the convergence rate, the concussion condition in the training period and the error between actual output and desired output. The exclusive-or (XOR) and Wisconsin breast cancer (WBC) classification tasks are employed to validate the proposed optimized methods. Experimental results demonstrate that compared to original learning algorithm, all three methods have less iterations, higher accuracy, and more stable in the training period.",

keywords = "learning performance, optimization method, Spiking Neural Network",

author = "Qiang Fu and Yuling Luo and Junxiu Liu and Jinjie Bi and Senhui Qiu and Yi Cao and Xuemei Ding",

year = "2018",

month = may,

day = "17",

doi = "10.1109/ICCT.2017.8359963",

language = "English",

series = "International Conference on Communication Technology Proceedings, ICCT",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "1916--1919",

booktitle = "2017 17th IEEE International Conference on Communication Technology, ICCT 2017",

note = "17th IEEE International Conference on Communication Technology, ICCT 2017 ; Conference date: 27-10-2017 Through 30-10-2017",

}

Fu, Q, Luo, Y, Liu, J, Bi, J, Qiu, S, Cao, Y & Ding, X 2018, Improving learning algorithm performance for spiking neural networks. in 2017 17th IEEE International Conference on Communication Technology, ICCT 2017. International Conference on Communication Technology Proceedings, ICCT, vol. 2017-October, Institute of Electrical and Electronics Engineers, pp. 1916-1919, 17th IEEE International Conference on Communication Technology, ICCT 2017, Chengdu, China, 27/10/17. https://doi.org/10.1109/ICCT.2017.8359963

Improving learning algorithm performance for spiking neural networks. / Fu, Qiang; Luo, Yuling; Liu, Junxiu et al.
2017 17th IEEE International Conference on Communication Technology, ICCT 2017. Institute of Electrical and Electronics Engineers, 2018. p. 1916-1919 (International Conference on Communication Technology Proceedings, ICCT; Vol. 2017-October).

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

TY - GEN

T1 - Improving learning algorithm performance for spiking neural networks

AU - Fu, Qiang

AU - Luo, Yuling

AU - Liu, Junxiu

AU - Bi, Jinjie

AU - Qiu, Senhui

AU - Cao, Yi

AU - Ding, Xuemei

PY - 2018/5/17

Y1 - 2018/5/17

N2 - This paper proposes three methods to improve the learning algorithm for spiking neural networks (SNNs). The aim is to improve learning performance in SNNs where neurons are allowed to fire multiple times. The performance is analyzed based on the convergence rate, the concussion condition in the training period and the error between actual output and desired output. The exclusive-or (XOR) and Wisconsin breast cancer (WBC) classification tasks are employed to validate the proposed optimized methods. Experimental results demonstrate that compared to original learning algorithm, all three methods have less iterations, higher accuracy, and more stable in the training period.

AB - This paper proposes three methods to improve the learning algorithm for spiking neural networks (SNNs). The aim is to improve learning performance in SNNs where neurons are allowed to fire multiple times. The performance is analyzed based on the convergence rate, the concussion condition in the training period and the error between actual output and desired output. The exclusive-or (XOR) and Wisconsin breast cancer (WBC) classification tasks are employed to validate the proposed optimized methods. Experimental results demonstrate that compared to original learning algorithm, all three methods have less iterations, higher accuracy, and more stable in the training period.

KW - learning performance

KW - optimization method

KW - Spiking Neural Network

UR - http://www.scopus.com/inward/record.url?scp=85047758431&partnerID=8YFLogxK

U2 - 10.1109/ICCT.2017.8359963

DO - 10.1109/ICCT.2017.8359963

M3 - Conference contribution

AN - SCOPUS:85047758431

T3 - International Conference on Communication Technology Proceedings, ICCT

SP - 1916

EP - 1919

BT - 2017 17th IEEE International Conference on Communication Technology, ICCT 2017

PB - Institute of Electrical and Electronics Engineers

T2 - 17th IEEE International Conference on Communication Technology, ICCT 2017

Y2 - 27 October 2017 through 30 October 2017

ER -

Fu Q, Luo Y, Liu J, Bi J, Qiu S, Cao Y et al. Improving learning algorithm performance for spiking neural networks. In 2017 17th IEEE International Conference on Communication Technology, ICCT 2017. Institute of Electrical and Electronics Engineers. 2018. p. 1916-1919. (International Conference on Communication Technology Proceedings, ICCT). doi: 10.1109/ICCT.2017.8359963

Improving learning algorithm performance for spiking neural networks

Abstract / Description of output

Publication series

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Fingerprint

Cite this