Neuromorphic Analog Implementation of Reservoir Computing for Machine Learning

Avi Hazan; Elishai Ezra Tsur

doi:10.1109/ICECS202256217.2022.9971045

Neuromorphic Analog Implementation of Reservoir Computing for Machine Learning

Avi Hazan, Elishai Ezra Tsur

Computer Science

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

Abstract

In reservoir computing, dynamical systems are used to drive state-of-the-art machine learning with small training sets and minimal computing resources. Neuromorphic (brain-inspired) computing pose to further improve reservoir computing with energy-efficient spiking neural implementations. Here we propose an analog circuit design for reservoir computing using OZ spiking neurons, STDP (Spike-timing-dependent plasticity) synapses, and learning PES (prescribed error sensitivity) circuitry. We evaluated our design on a small scale using the Iris flower data set, demonstrating the potential application of neuromorphic analog hardware in reservoir computing.

Original language	American English
Title of host publication	ICECS 2022
Subtitle of host publication	29th IEEE International Conference on Electronics, Circuits and Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-4
Number of pages	4
ISBN (Electronic)	9781665488235
DOIs	https://doi.org/10.1109/ICECS202256217.2022.9971045
State	Published - 2022
Event	29th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2022 - Glasgow, United Kingdom Duration: 24 Oct 2022 → 26 Oct 2022

Publication series

Name	ICECS 2022 - 29th IEEE International Conference on Electronics, Circuits and Systems, Proceedings

Conference

Conference	29th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2022
Country/Territory	United Kingdom
City	Glasgow
Period	24/10/22 → 26/10/22

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This work was supported by the Open University of Israel research grant. The authors would like to thank the members of the Neuro-Biomorphic Engineering Lab at the Open University of Israel for the fruitful discussions.

Publisher Copyright:
© 2022 IEEE.

Keywords

iris flower dataset
OZ neuron
PES
Spiking neural networks
STDP

Access to Document

10.1109/ICECS202256217.2022.9971045

Cite this

Hazan, A., & Tsur, E. E. (2022). Neuromorphic Analog Implementation of Reservoir Computing for Machine Learning. In ICECS 2022: 29th IEEE International Conference on Electronics, Circuits and Systems (pp. 1-4). (ICECS 2022 - 29th IEEE International Conference on Electronics, Circuits and Systems, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICECS202256217.2022.9971045

Hazan, Avi ; Tsur, Elishai Ezra. / Neuromorphic Analog Implementation of Reservoir Computing for Machine Learning. ICECS 2022: 29th IEEE International Conference on Electronics, Circuits and Systems. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 1-4 (ICECS 2022 - 29th IEEE International Conference on Electronics, Circuits and Systems, Proceedings).

@inproceedings{a04cd6321fb146f4bcd0b3b2bc5ea033,

title = "Neuromorphic Analog Implementation of Reservoir Computing for Machine Learning",

abstract = "In reservoir computing, dynamical systems are used to drive state-of-the-art machine learning with small training sets and minimal computing resources. Neuromorphic (brain-inspired) computing pose to further improve reservoir computing with energy-efficient spiking neural implementations. Here we propose an analog circuit design for reservoir computing using OZ spiking neurons, STDP (Spike-timing-dependent plasticity) synapses, and learning PES (prescribed error sensitivity) circuitry. We evaluated our design on a small scale using the Iris flower data set, demonstrating the potential application of neuromorphic analog hardware in reservoir computing.",

keywords = "iris flower dataset, OZ neuron, PES, Spiking neural networks, STDP",

author = "Avi Hazan and Tsur, \{Elishai Ezra\}",

note = "Funding Information: ACKNOWLEDGMENT This work was supported by the Open University of Israel research grant. The authors would like to thank the members of the Neuro-Biomorphic Engineering Lab at the Open University of Israel for the fruitful discussions. Publisher Copyright: {\textcopyright} 2022 IEEE.; 29th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2022 ; Conference date: 24-10-2022 Through 26-10-2022",

year = "2022",

doi = "10.1109/ICECS202256217.2022.9971045",

language = "American English",

series = "ICECS 2022 - 29th IEEE International Conference on Electronics, Circuits and Systems, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--4",

booktitle = "ICECS 2022",

address = "United States",

}

Hazan, A & Tsur, EE 2022, Neuromorphic Analog Implementation of Reservoir Computing for Machine Learning. in ICECS 2022: 29th IEEE International Conference on Electronics, Circuits and Systems. ICECS 2022 - 29th IEEE International Conference on Electronics, Circuits and Systems, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 29th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2022, Glasgow, United Kingdom, 24/10/22. https://doi.org/10.1109/ICECS202256217.2022.9971045

Neuromorphic Analog Implementation of Reservoir Computing for Machine Learning. / Hazan, Avi; Tsur, Elishai Ezra.
ICECS 2022: 29th IEEE International Conference on Electronics, Circuits and Systems. Institute of Electrical and Electronics Engineers Inc., 2022. p. 1-4 (ICECS 2022 - 29th IEEE International Conference on Electronics, Circuits and Systems, Proceedings).

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

TY - GEN

T1 - Neuromorphic Analog Implementation of Reservoir Computing for Machine Learning

AU - Hazan, Avi

AU - Tsur, Elishai Ezra

N1 - Funding Information: ACKNOWLEDGMENT This work was supported by the Open University of Israel research grant. The authors would like to thank the members of the Neuro-Biomorphic Engineering Lab at the Open University of Israel for the fruitful discussions. Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - In reservoir computing, dynamical systems are used to drive state-of-the-art machine learning with small training sets and minimal computing resources. Neuromorphic (brain-inspired) computing pose to further improve reservoir computing with energy-efficient spiking neural implementations. Here we propose an analog circuit design for reservoir computing using OZ spiking neurons, STDP (Spike-timing-dependent plasticity) synapses, and learning PES (prescribed error sensitivity) circuitry. We evaluated our design on a small scale using the Iris flower data set, demonstrating the potential application of neuromorphic analog hardware in reservoir computing.

AB - In reservoir computing, dynamical systems are used to drive state-of-the-art machine learning with small training sets and minimal computing resources. Neuromorphic (brain-inspired) computing pose to further improve reservoir computing with energy-efficient spiking neural implementations. Here we propose an analog circuit design for reservoir computing using OZ spiking neurons, STDP (Spike-timing-dependent plasticity) synapses, and learning PES (prescribed error sensitivity) circuitry. We evaluated our design on a small scale using the Iris flower data set, demonstrating the potential application of neuromorphic analog hardware in reservoir computing.

KW - iris flower dataset

KW - OZ neuron

KW - PES

KW - Spiking neural networks

KW - STDP

UR - https://www.scopus.com/pages/publications/85145355999

U2 - 10.1109/ICECS202256217.2022.9971045

DO - 10.1109/ICECS202256217.2022.9971045

M3 - Conference contribution

T3 - ICECS 2022 - 29th IEEE International Conference on Electronics, Circuits and Systems, Proceedings

SP - 1

EP - 4

BT - ICECS 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 29th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2022

Y2 - 24 October 2022 through 26 October 2022

ER -

Hazan A, Tsur EE. Neuromorphic Analog Implementation of Reservoir Computing for Machine Learning. In ICECS 2022: 29th IEEE International Conference on Electronics, Circuits and Systems. Institute of Electrical and Electronics Engineers Inc. 2022. p. 1-4. (ICECS 2022 - 29th IEEE International Conference on Electronics, Circuits and Systems, Proceedings). doi: 10.1109/ICECS202256217.2022.9971045

Neuromorphic Analog Implementation of Reservoir Computing for Machine Learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this