Modeling memristor-based neural networks with Manhattan update: Trade-offs in learning performance and energy consumption
APL Electronic Devices · 01.06.2026 · 2 (2)
DOI: 10.1063/5.0310714 ↗Kurz gefasst
Fachartikel in der Zeitschrift APL Electronic Devices, online erschienen am 01.04.2026. Verfasst von Walter Quiñonez und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission.
Abstract (Originalsprache)
We present a systematic study of memristor-based neural networks trained with the hardware-friendly Manhattan update rule, focusing on the trade-offs between learning performance and energy consumption. Using realistic models of potentiation/depression (P/D) curves, we evaluate the impact of nonlinearity (NLI), conductance range, and number of accessible levels on both a single perceptron and a multilayer perceptron (MLP) trained on the MNIST dataset. Our results show that SPs tolerate P/D nonlinearity up to NLI ≤ 10−2, while MLPs require stricter conditions of NLI ≤ 10−3 to preserve accuracy. Increasing the number of discrete conductance states improves convergence, effectively acting as a finer learning rate. We further propose a strategy where one memristor of each differential pair is fixed, reducing redundant memristor conductance updates. This approach lowers training energy by nearly 50% in MLP with little to no loss in accuracy. Our findings highlight the importance of device–algorithm co-design in enabling scalable, low-power neuromorphic hardware for edge artificial intelligence (AI) applications.
Förderung
- European Commission
Zitieren
APA
Quiñonez, W., Sánchez, M. J., & Rubi, D. (2026). Modeling memristor-based neural networks with Manhattan update: Trade-offs in learning performance and energy consumption. APL Electronic Devices, 2(2). https://doi.org/10.1063/5.0310714
Vancouver
Quiñonez W, Sánchez MJ, Rubi D. Modeling memristor-based neural networks with Manhattan update: Trade-offs in learning performance and energy consumption. APL Electronic Devices. 2026;2(2). doi:10.1063/5.0310714
BibTeX
@article{Quionez2026,
author = {Quiñonez, Walter and Sánchez, María José and Rubi, Diego},
title = {Modeling memristor-based neural networks with Manhattan update: Trade-offs in learning performance and energy consumption},
journal = {APL Electronic Devices},
year = {2026},
volume = {2},
number = {2},
doi = {10.1063/5.0310714}
}
EUVIMED