Robust Mapping of a Software‐Trained Adiabatic Capacitive Artificial Neuron
Electronics Letters · 2026-01 · 62 (1)
DOI: 10.1049/ell2.70560 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics Letters, online erschienen am 17.03.2026. Verfasst von Michael Smart und 3 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Defence Science and Technology Laboratory.
Abstract (Originalsprache)
The adiabatic capacitive artificial neuron (ACAN) has been previously shown to offer the potential for ultra‐low power computation in full custom analogue ASIC designs. However, it did not consider how a real‐world, software‐trained, artificial neuron (AN) could be mapped robustly onto the circuit. In this paper, we describe how an AN, with positive‐valued weights, bias and a binary activation function, can be mapped directly and precisely onto an ACAN. The functional equivalence and properties of the mapping are demonstrated with ANs extracted from an artificial neural network (ANN) trained against a binarized MNIST dataset using an open‐source software AI framework.
Förderung
- Defence Science and Technology Laboratory
Zitieren
APA
Smart, M., Maheshwari, S., Raghav, H. S., & Serb, A. (2026). Robust Mapping of a Software‐Trained Adiabatic Capacitive Artificial Neuron. Electronics Letters, 62(1). https://doi.org/10.1049/ell2.70560
Vancouver
Smart M, Maheshwari S, Raghav HS, Serb A. Robust Mapping of a Software‐Trained Adiabatic Capacitive Artificial Neuron. Electronics Letters. 2026;62(1). doi:10.1049/ell2.70560
BibTeX
@article{Smart2026,
author = {Smart, Michael and Maheshwari, Sachin and Raghav, Himadri Singh and Serb, Alex},
title = {Robust Mapping of a Software‐Trained Adiabatic Capacitive Artificial Neuron},
journal = {Electronics Letters},
year = {2026},
volume = {62},
number = {1},
doi = {10.1049/ell2.70560}
}
EUVIMED