Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions

Arindam Basu; Charlotte Frenkel; Lei Deng; Xueyong Zhang

doi:10.1109/CICC53496.2022.9772783

Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions

Arindam Basu
, Charlotte Frenkel
, Lei Deng
, Xueyong Zhang

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

97 Citations (Scopus)

Abstract

The rapid growth of deep learning, spurred by its successes in various fields ranging from face recognition [1] to game playing [2], has also triggered a growing interest in the design of specialized hardware accelerators to support these algorithms. This specialized hardware targets one of two categories-either operating in datacenters or on mobile devices at the network edge. While energy efficiency is important in both cases, the need is extremely stringent in the latter class of applications due to limited battery life. Several techniques have been used in the past to improve the energy efficiency of these accelerators [3], including reducing off-chip DRAM access, managing data flow across processing elements as well as in-memory computing (IMC) by exploiting analog processing of data within digital memory arrays [4].

Original language	English
Title of host publication	2022 IEEE Custom Integrated Circuits Conference (CICC) - Proceedings
Publisher	IEEE
Number of pages	8
ISBN (Electronic)	9781665407564
ISBN (Print)	9781728182803
DOIs	https://doi.org/10.1109/CICC53496.2022.9772783
Publication status	Published - 2022
Event	43rd IEEE Custom Integrated Circuits Conference (CICC 2022) - Hybrid, Newport Beach, United States Duration: 24 Apr 2022 → 27 Apr 2022 http://www.ieee-cicc.org

Publication series

Name	Proceedings of the Custom Integrated Circuits Conference
Volume	2022-April
ISSN (Print)	0886-5930
ISSN (Electronic)	2152-3630

Conference

Conference	43rd IEEE Custom Integrated Circuits Conference (CICC 2022)
Abbreviated title	IEEE CICC 2022
Place	United States
City	Newport Beach
Period	24/04/22 → 27/04/22
Internet address	http://www.ieee-cicc.org

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Access Output

10.1109/CICC53496.2022.9772783

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{043224f1541f45f2b9c39280258d3bf6,

title = "Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions",

abstract = "The rapid growth of deep learning, spurred by its successes in various fields ranging from face recognition [1] to game playing [2], has also triggered a growing interest in the design of specialized hardware accelerators to support these algorithms. This specialized hardware targets one of two categories-either operating in datacenters or on mobile devices at the network edge. While energy efficiency is important in both cases, the need is extremely stringent in the latter class of applications due to limited battery life. Several techniques have been used in the past to improve the energy efficiency of these accelerators [3], including reducing off-chip DRAM access, managing data flow across processing elements as well as in-memory computing (IMC) by exploiting analog processing of data within digital memory arrays [4].",

author = "Arindam Basu and Charlotte Frenkel and Lei Deng and Xueyong Zhang",

year = "2022",

doi = "10.1109/CICC53496.2022.9772783",

language = "English",

isbn = "9781728182803",

series = "Proceedings of the Custom Integrated Circuits Conference",

publisher = "IEEE",

booktitle = "2022 IEEE Custom Integrated Circuits Conference (CICC) - Proceedings",

address = "United States",

note = "43rd IEEE Custom Integrated Circuits Conference (CICC 2022), IEEE CICC 2022 ; Conference date: 24-04-2022 Through 27-04-2022",

url = "http://www.ieee-cicc.org",

}

Basu, A, Frenkel, C, Deng, L & Zhang, X 2022, Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions. in 2022 IEEE Custom Integrated Circuits Conference (CICC) - Proceedings. Proceedings of the Custom Integrated Circuits Conference, vol. 2022-April, IEEE, 43rd IEEE Custom Integrated Circuits Conference (CICC 2022), Newport Beach, California, United States, 24/04/22. https://doi.org/10.1109/CICC53496.2022.9772783

Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions. / Basu, Arindam; Frenkel, Charlotte; Deng, Lei et al.
2022 IEEE Custom Integrated Circuits Conference (CICC) - Proceedings. IEEE, 2022. (Proceedings of the Custom Integrated Circuits Conference; Vol. 2022-April).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Spiking Neural Network Integrated Circuits

T2 - 43rd IEEE Custom Integrated Circuits Conference (CICC 2022)

AU - Basu, Arindam

AU - Frenkel, Charlotte

AU - Deng, Lei

AU - Zhang, Xueyong

PY - 2022

Y1 - 2022

N2 - The rapid growth of deep learning, spurred by its successes in various fields ranging from face recognition [1] to game playing [2], has also triggered a growing interest in the design of specialized hardware accelerators to support these algorithms. This specialized hardware targets one of two categories-either operating in datacenters or on mobile devices at the network edge. While energy efficiency is important in both cases, the need is extremely stringent in the latter class of applications due to limited battery life. Several techniques have been used in the past to improve the energy efficiency of these accelerators [3], including reducing off-chip DRAM access, managing data flow across processing elements as well as in-memory computing (IMC) by exploiting analog processing of data within digital memory arrays [4].

AB - The rapid growth of deep learning, spurred by its successes in various fields ranging from face recognition [1] to game playing [2], has also triggered a growing interest in the design of specialized hardware accelerators to support these algorithms. This specialized hardware targets one of two categories-either operating in datacenters or on mobile devices at the network edge. While energy efficiency is important in both cases, the need is extremely stringent in the latter class of applications due to limited battery life. Several techniques have been used in the past to improve the energy efficiency of these accelerators [3], including reducing off-chip DRAM access, managing data flow across processing elements as well as in-memory computing (IMC) by exploiting analog processing of data within digital memory arrays [4].

UR - https://www.scopus.com/pages/publications/85130754544

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85130754544&origin=recordpage

U2 - 10.1109/CICC53496.2022.9772783

DO - 10.1109/CICC53496.2022.9772783

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781728182803

T3 - Proceedings of the Custom Integrated Circuits Conference

BT - 2022 IEEE Custom Integrated Circuits Conference (CICC) - Proceedings

PB - IEEE

Y2 - 24 April 2022 through 27 April 2022

ER -

Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions

Abstract

Publication series

Conference

UN SDGs

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this