Digital neuromorphic implementation of the biologically inspired pallidal oscillator

Shuangming Yang, Xinyu Hao, Jiang Wang, Huiyan Li, Bin Deng, Yanqiu Che

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

Abstract

This paper proposes a modified biologically conductance-based pallidal oscillator model, targeting low-cost and multiplierless implementation with relevant and reliable dynamical characteristics on digital neuromorphic platform. High-Accuracy neural computation is limited in scale and efficiency by available hardware resources, so there are significant demands for costefficient hardware circuits in the large-scale simulations of neuromorphic field. Thus, the feasibility of a digital implementation with lower hardware overhead cost is investigated in this paper. Implementation results on a field-programmable gate array device demonstrate that the presented model can reduce the hardware resource cost significantly compared to the conventional look-up-Table-based design. The proposed methology is an essential step towards the real-Time implementation of large-scale spiking neural network, and is meaningful for the investigation on the neurodegenerative diseases and its model-based closed-loop control. It can also be applied in the real-Time control of the bio-inspired neurorobotics.

Original languageEnglish (US)
Title of host publicationProceedings of 2018 International Conference on Intelligent Science and Technology, ICIST 2018
PublisherAssociation for Computing Machinery
Pages23-28
Number of pages6
ISBN (Electronic)9781450364614
DOIs
StatePublished - Jun 30 2018
Event2018 International Conference on Intelligent Science and Technology, ICIST 2018 - London, United Kingdom
Duration: Jun 30 2018Jul 2 2018

Publication series

NameACM International Conference Proceeding Series

Other

Other2018 International Conference on Intelligent Science and Technology, ICIST 2018
CountryUnited Kingdom
CityLondon
Period6/30/187/2/18

Fingerprint

Hardware
Neurodegenerative diseases
Costs
Real time control
Field programmable gate arrays (FPGA)
Neural networks
Networks (circuits)

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Cite this

Yang, S., Hao, X., Wang, J., Li, H., Deng, B., & Che, Y. (2018). Digital neuromorphic implementation of the biologically inspired pallidal oscillator. In Proceedings of 2018 International Conference on Intelligent Science and Technology, ICIST 2018 (pp. 23-28). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3233740.3233748
Yang, Shuangming ; Hao, Xinyu ; Wang, Jiang ; Li, Huiyan ; Deng, Bin ; Che, Yanqiu. / Digital neuromorphic implementation of the biologically inspired pallidal oscillator. Proceedings of 2018 International Conference on Intelligent Science and Technology, ICIST 2018. Association for Computing Machinery, 2018. pp. 23-28 (ACM International Conference Proceeding Series).
@inproceedings{b56d09b62ca1417789bd18a6a172422d,
title = "Digital neuromorphic implementation of the biologically inspired pallidal oscillator",
abstract = "This paper proposes a modified biologically conductance-based pallidal oscillator model, targeting low-cost and multiplierless implementation with relevant and reliable dynamical characteristics on digital neuromorphic platform. High-Accuracy neural computation is limited in scale and efficiency by available hardware resources, so there are significant demands for costefficient hardware circuits in the large-scale simulations of neuromorphic field. Thus, the feasibility of a digital implementation with lower hardware overhead cost is investigated in this paper. Implementation results on a field-programmable gate array device demonstrate that the presented model can reduce the hardware resource cost significantly compared to the conventional look-up-Table-based design. The proposed methology is an essential step towards the real-Time implementation of large-scale spiking neural network, and is meaningful for the investigation on the neurodegenerative diseases and its model-based closed-loop control. It can also be applied in the real-Time control of the bio-inspired neurorobotics.",
author = "Shuangming Yang and Xinyu Hao and Jiang Wang and Huiyan Li and Bin Deng and Yanqiu Che",
year = "2018",
month = "6",
day = "30",
doi = "10.1145/3233740.3233748",
language = "English (US)",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "23--28",
booktitle = "Proceedings of 2018 International Conference on Intelligent Science and Technology, ICIST 2018",

}

Yang, S, Hao, X, Wang, J, Li, H, Deng, B & Che, Y 2018, Digital neuromorphic implementation of the biologically inspired pallidal oscillator. in Proceedings of 2018 International Conference on Intelligent Science and Technology, ICIST 2018. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 23-28, 2018 International Conference on Intelligent Science and Technology, ICIST 2018, London, United Kingdom, 6/30/18. https://doi.org/10.1145/3233740.3233748

Digital neuromorphic implementation of the biologically inspired pallidal oscillator. / Yang, Shuangming; Hao, Xinyu; Wang, Jiang; Li, Huiyan; Deng, Bin; Che, Yanqiu.

Proceedings of 2018 International Conference on Intelligent Science and Technology, ICIST 2018. Association for Computing Machinery, 2018. p. 23-28 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Digital neuromorphic implementation of the biologically inspired pallidal oscillator

AU - Yang, Shuangming

AU - Hao, Xinyu

AU - Wang, Jiang

AU - Li, Huiyan

AU - Deng, Bin

AU - Che, Yanqiu

PY - 2018/6/30

Y1 - 2018/6/30

N2 - This paper proposes a modified biologically conductance-based pallidal oscillator model, targeting low-cost and multiplierless implementation with relevant and reliable dynamical characteristics on digital neuromorphic platform. High-Accuracy neural computation is limited in scale and efficiency by available hardware resources, so there are significant demands for costefficient hardware circuits in the large-scale simulations of neuromorphic field. Thus, the feasibility of a digital implementation with lower hardware overhead cost is investigated in this paper. Implementation results on a field-programmable gate array device demonstrate that the presented model can reduce the hardware resource cost significantly compared to the conventional look-up-Table-based design. The proposed methology is an essential step towards the real-Time implementation of large-scale spiking neural network, and is meaningful for the investigation on the neurodegenerative diseases and its model-based closed-loop control. It can also be applied in the real-Time control of the bio-inspired neurorobotics.

AB - This paper proposes a modified biologically conductance-based pallidal oscillator model, targeting low-cost and multiplierless implementation with relevant and reliable dynamical characteristics on digital neuromorphic platform. High-Accuracy neural computation is limited in scale and efficiency by available hardware resources, so there are significant demands for costefficient hardware circuits in the large-scale simulations of neuromorphic field. Thus, the feasibility of a digital implementation with lower hardware overhead cost is investigated in this paper. Implementation results on a field-programmable gate array device demonstrate that the presented model can reduce the hardware resource cost significantly compared to the conventional look-up-Table-based design. The proposed methology is an essential step towards the real-Time implementation of large-scale spiking neural network, and is meaningful for the investigation on the neurodegenerative diseases and its model-based closed-loop control. It can also be applied in the real-Time control of the bio-inspired neurorobotics.

UR - http://www.scopus.com/inward/record.url?scp=85055888927&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055888927&partnerID=8YFLogxK

U2 - 10.1145/3233740.3233748

DO - 10.1145/3233740.3233748

M3 - Conference contribution

T3 - ACM International Conference Proceeding Series

SP - 23

EP - 28

BT - Proceedings of 2018 International Conference on Intelligent Science and Technology, ICIST 2018

PB - Association for Computing Machinery

ER -

Yang S, Hao X, Wang J, Li H, Deng B, Che Y. Digital neuromorphic implementation of the biologically inspired pallidal oscillator. In Proceedings of 2018 International Conference on Intelligent Science and Technology, ICIST 2018. Association for Computing Machinery. 2018. p. 23-28. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3233740.3233748