Saved in:
Bibliographic Details
Main Authors: Maheshwari, Sachin, Smart, Mike, Raghav, Himadri Singh, Prodromakis, Themis, Serb, Alexander
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.00831
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910041949339648
author Maheshwari, Sachin
Smart, Mike
Raghav, Himadri Singh
Prodromakis, Themis
Serb, Alexander
author_facet Maheshwari, Sachin
Smart, Mike
Raghav, Himadri Singh
Prodromakis, Themis
Serb, Alexander
contents This paper introduces a new, highly energy-efficient, Adiabatic Capacitive Neuron (ACN) hardware implementation of an Artificial Neuron (AN) with improved functionality, accuracy, robustness and scalability over previous work. The paper describes the implementation of a \mbox{12-bit} single neuron, with positive and negative weight support, in an $\mathbf{0.18μm}$ CMOS technology. The paper also presents a new Threshold Logic (TL) design for a binary AN activation function that generates a low symmetrical offset across three process corners and five temperatures between $-55^o$C and $125^o$C. Post-layout simulations demonstrate a maximum rising and falling offset voltage of 9$mV$ compared to conventional TL, which has rising and falling offset voltages of 27$mV$ and 5$mV$ respectively, across temperature and process. Moreover, the proposed TL design shows a decrease in average energy of 1.5$\%$ at the SS corner and 2.3$\%$ at FF corner compared to the conventional TL design. The total synapse energy saving for the proposed ACN was above 90$\%$ (over 12x improvement) when compared to a non-adiabatic CMOS Capacitive Neuron (CCN) benchmark for a frequency ranging from 500$kHz$ to 100$MHz$. A 1000-sample Monte Carlo simulation including process variation and mismatch confirms the worst-case energy savings of $\>$90$\%$ compared to CCN in the synapse energy profile. Finally, the impact of supply voltage scaling shows consistent energy savings of above 90$\%$ (except all zero inputs) without loss of functionality.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00831
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adiabatic Capacitive Neuron: An Energy-Efficient Functional Unit for Artificial Neural Networks
Maheshwari, Sachin
Smart, Mike
Raghav, Himadri Singh
Prodromakis, Themis
Serb, Alexander
Image and Video Processing
This paper introduces a new, highly energy-efficient, Adiabatic Capacitive Neuron (ACN) hardware implementation of an Artificial Neuron (AN) with improved functionality, accuracy, robustness and scalability over previous work. The paper describes the implementation of a \mbox{12-bit} single neuron, with positive and negative weight support, in an $\mathbf{0.18μm}$ CMOS technology. The paper also presents a new Threshold Logic (TL) design for a binary AN activation function that generates a low symmetrical offset across three process corners and five temperatures between $-55^o$C and $125^o$C. Post-layout simulations demonstrate a maximum rising and falling offset voltage of 9$mV$ compared to conventional TL, which has rising and falling offset voltages of 27$mV$ and 5$mV$ respectively, across temperature and process. Moreover, the proposed TL design shows a decrease in average energy of 1.5$\%$ at the SS corner and 2.3$\%$ at FF corner compared to the conventional TL design. The total synapse energy saving for the proposed ACN was above 90$\%$ (over 12x improvement) when compared to a non-adiabatic CMOS Capacitive Neuron (CCN) benchmark for a frequency ranging from 500$kHz$ to 100$MHz$. A 1000-sample Monte Carlo simulation including process variation and mismatch confirms the worst-case energy savings of $\>$90$\%$ compared to CCN in the synapse energy profile. Finally, the impact of supply voltage scaling shows consistent energy savings of above 90$\%$ (except all zero inputs) without loss of functionality.
title Adiabatic Capacitive Neuron: An Energy-Efficient Functional Unit for Artificial Neural Networks
topic Image and Video Processing
url https://arxiv.org/abs/2507.00831