More Web Proxy on the site http://driver.im/

research-article

Analog Circuit Implementation of Neurons with Multiply-Accumulate and ReLU Functions

Authors:

Terry Tao YeAuthors Info & Claims

GLSVLSI '20: Proceedings of the 2020 on Great Lakes Symposium on VLSI

Pages 493 - 498

https://doi.org/10.1145/3386263.3406941

Published: 07 September 2020 Publication History

Abstract

Although Artificial Neural Networks (ANNs) are inspired by biological neural systems, most of ANNs today are implemented with digital circuitry and use binary values in computation. In recent years, analog-based neuromorphic system has gained lots of attention as it provides a natural interface for brain-machine interaction. In this paper, we present analog designs of a complete neuron system, where the Multiply-Accumulate (MAC) and Rectified Linear Unit (ReLU) functions are all implemented in analog circuits. The design uses SMIC 55nm standard LP CMOS process node and operates at low supply voltage (1.2 V). The simulation results in SPECTRE demonstrate that the MAC's linear error is no more than 0.5% and total harmonic distortion (THD) is less than 1.6% when the inputs vary from peak (-10 µA) to peak (10 µA) at 10 MHz, the -3dB bandwidth is 288 MHz, the maximum power consumption is 540 µW and the static power consumption is 493 µW under 100MHz input signal frequency. More specifically, our design is resilient to the fluctuation of power supply, which helps to achieve high precision of computation.

Supplementary Material

MP4 File (3386263.3406941.mp4)

Presentation video

Download
11.47 MB

References

[1]

Schuman, C.D. et al. 2017. A Survey of Neuromorphic Computing and Neural Networks in Hardware. arXiv. (2017), 1--88.

[2]

Don Monroe. 2014. Neuromorphic computing gets ready for the (really) big time. Communications of the ACM. 57, 6: 13--15.

Digital Library

[3]

McCulloch, W. and Pitts, W. 1943. A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics. 5, 4 (1943), 115--133.

[4]

Beyraghi, N. and Khoei, A. 2014. CMOS design of a low power and high precision four-quadrant analog multiplier. AEU - International Journal of Electronics and Communications. 69, 1 (2014), 400--407.

[5]

Ghomi, A. and Dolatshahi, M. 2018. Design of a new CMOS Low-Power Analogue Neuron. IETE Journal of Research. 64, 1 (2018), 67--75.

[6]

Aloui, I. et al. 2018. ± 0.75V Four Quadrant Analog Multiplier In Current. 2018 15th International Multi-Conference on Systems, Signals & Devices (SSD). 1 (2018), 1045--1050.

[7]

Satansup, J. and Tangsrirat, W. 2018. 1.5-V CMOS Current Multiplier / Divider. 2018 International Journal of Electrical and Computer Engineering (IJECE). 8, 3 (2018), 1478--1487.

[8]

Aloui, I. et al. 2017. A CMOS current mode four quadrant analog multiplier free from mobility reduction. AEU - International Journal of Electronics and Communications. 82, (2017), 119--126.

[9]

Maryan, M.M. et al. 2018. Low-Power High-Speed Analog Multiplier/Divider Based on a New Current Squarer Circuit. Arabian Journal for Science and Engineering. 43, 6 (2018), 2909--2918.

[10]

Yoo, C. and Park, J. 2007. Triage; a literature review of key concepts. Electronics Letters. 43, 25 (2007), 1422--1424.

[11]

Aloui, I. et al. 2017. Low-Voltage low-Power Four-Quadrant Analog Multiplier In Current-Mode. 18th International Conference on Sciences and Techniques of Automatic control & computer engineering. 4, 5 (2017), 163--167.

[12]

Naderi, A. et al. 2009. A new high speed and low power four-quadrant CMOS analog multiplier in current mode. AEU - International Journal of Electronics and Communications. 63, 9 (2009), 769--775.

[13]

Priyanka, P. et al. 2019. CMOS Implementation of Rectfied Linear Activation Function. VLSI Design and Test. (2019), 121--129.

[14]

Yilmaz, M. et al. 2014. High-efficiency passive full wave rectification for electromagnetic harvesters. Journal of Applied Physics. 116, 13 (2014).

[15]

Peters, C. et al. 2011. A sub-500 mV highly efficient active rectifier for energy harvesting applications. IEEE Transactions on Circuits and Systems I: Regular Papers. 58, 7 (2011), 1542--1550.

Cited By

My Abdelouahed SMohamed EAbdellah A(2024)Implementing Analog Artificial Neural Networks for Enhanced Energy Efficiency and Speed in Machine Learning Applications2024 International Conference on Intelligent Systems and Computer Vision (ISCV)10.1109/ISCV60512.2024.10620095(1-6)Online publication date: 8-May-2024
https://doi.org/10.1109/ISCV60512.2024.10620095
Edwards JParker LCardwell SChance FKoziol S(2024)Neural-Inspired Dendritic Multiplication Using a Reconfigurable Analog Integrated Circuit2024 IEEE International Symposium on Circuits and Systems (ISCAS)10.1109/ISCAS58744.2024.10557895(1-5)Online publication date: 19-May-2024
https://doi.org/10.1109/ISCAS58744.2024.10557895
Li GSekine RNehra RGray RLedezma LGuo QMarandi A(2022)All-optical ultrafast ReLU function for energy-efficient nanophotonic deep learningNanophotonics10.1515/nanoph-2022-013712:5(847-855)Online publication date: 2-May-2022
https://doi.org/10.1515/nanoph-2022-0137
Show More Cited By

Index Terms

Analog Circuit Implementation of Neurons with Multiply-Accumulate and ReLU Functions
1. Hardware
  1. Integrated circuits
  2. Very large scale integration design
    1. Application-specific VLSI designs
      1. Application specific integrated circuits

Recommendations

Analog Circuit Implementation of LIF and STDP Models for Spiking Neural Networks
GLSVLSI '20: Proceedings of the 2020 on Great Lakes Symposium on VLSI

Spiking Neural Networks (SNN) is one special implementation of Artificial Neural Networks (ANN), where the input signals are encoded in the temporal relationship between consecutive spikes (spike trains) instead of real-numbered values. Nevertheless, ...
Analog implementation of neuron---astrocyte interaction in tripartite synapse

Neural synchronization is considered as an important mechanism for information processing. In addition, recent neurophysiological findings approve that astrocytes adjust the synaptic transmission of neural networks. Motivated by these observations, we ...
55nm CMOS analog circuit implementation of LIF and STDP functions for low-power SNNs
ISLPED '21: Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design

Spiking neural networks (SNNs) demonstrate great potentials to achieve low-power computation for AI applications. SNN uses spike trains, instead of binary bit-steams to encode input and output information, therefore, analog implementation of SNN will ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

GLSVLSI '20: Proceedings of the 2020 on Great Lakes Symposium on VLSI

September 2020

597 pages

ISBN:9781450379441

DOI:10.1145/3386263

General Chairs:
Tinoosh Mohsenin
University of Maryland, Baltimore County, USA
,
Weisheng Zhao
Beihang University, China
,
Program Chairs:
Yiran Chen
Duke University, USA
,
Onur Mutlu
ETH Zurich, Switzerland

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 September 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Key-Area Research and Development Program of GuangDong Province
High-level University Fund
University Key Laboratory of Advanced Wireless Communications of Guangdong Province

Conference

GLSVLSI '20

GLSVLSI '20: Great Lakes Symposium on VLSI 2020

September 7 - 9, 2020

Virtual Event, China

Acceptance Rates

Overall Acceptance Rate 312 of 1,156 submissions, 27%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
507
Total Downloads

Downloads (Last 12 months)101
Downloads (Last 6 weeks)19

Reflects downloads up to 10 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

My Abdelouahed SMohamed EAbdellah A(2024)Implementing Analog Artificial Neural Networks for Enhanced Energy Efficiency and Speed in Machine Learning Applications2024 International Conference on Intelligent Systems and Computer Vision (ISCV)10.1109/ISCV60512.2024.10620095(1-6)Online publication date: 8-May-2024
https://doi.org/10.1109/ISCV60512.2024.10620095
Edwards JParker LCardwell SChance FKoziol S(2024)Neural-Inspired Dendritic Multiplication Using a Reconfigurable Analog Integrated Circuit2024 IEEE International Symposium on Circuits and Systems (ISCAS)10.1109/ISCAS58744.2024.10557895(1-5)Online publication date: 19-May-2024
https://doi.org/10.1109/ISCAS58744.2024.10557895
Li GSekine RNehra RGray RLedezma LGuo QMarandi A(2022)All-optical ultrafast ReLU function for energy-efficient nanophotonic deep learningNanophotonics10.1515/nanoph-2022-013712:5(847-855)Online publication date: 2-May-2022
https://doi.org/10.1515/nanoph-2022-0137
Wang SAl-Tamimi KHammad IEl-Sankary K(2022)Towards Current-Mode Analog Implementation of Deep Neural Network Functions2022 20th IEEE Interregional NEWCAS Conference (NEWCAS)10.1109/NEWCAS52662.2022.9842017(322-326)Online publication date: 19-Jun-2022
https://doi.org/10.1109/NEWCAS52662.2022.9842017
Zhu JChen BYang ZMeng LYe T(2021)Analog Circuit Implementation of Neural Networks for In-Sensor Computing2021 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)10.1109/ISVLSI51109.2021.00037(150-156)Online publication date: Jul-2021
https://doi.org/10.1109/ISVLSI51109.2021.00037

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents