On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification
Advanced Electronic Materials · 04.05.2026
DOI: 10.1002/aelm.202500866 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Electronic Materials, online erschienen am 04.05.2026. Verfasst von Rishona Daniels und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: H2020 Future and Emerging Technologies, H2020 European Research Council.
Abstract (Originalsprache)
Reservoir computing (RC) is an emerging recurrent neural network architecture that has attracted growing attention for its low training cost and modest hardware requirements. Memristor‐based circuits are particularly promising for RC, as their intrinsic dynamics can reduce network size and parameter overhead in tasks such as time‐series prediction and image recognition. Although RC has been demonstrated with several memristive devices, a comprehensive evaluation of device‐level requirements remains limited. In this paper, we analyze and explain the operation of a parallel delayed feedback network (PDFN) RC architecture with volatile memristors, focusing on how device characteristics – such as decay rate, quantization, and variability – affect reservoir performance. We further discuss strategies to improve data representation in the reservoir using preprocessing methods and suggest potential improvements. The proposed approach achieves classification accuracy on MNIST, comparable with the best reported memristor‐based RC implementations. Furthermore, the method maintains high robustness under device variability, achieving an accuracy of up to . These results demonstrate that volatile memristors can support reliable spatio‐temporal information processing and reinforce their potential as key building blocks for compact, high‐speed, and energy‐efficient neuromorphic computing systems.
Förderung
- H2020 Future and Emerging Technologies
- H2020 European Research Council
Zitieren
APA
Daniels, R., Wattad, D., Ronen, R., Saad, D., & Kvatinsky, S. (2026). On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification. Advanced Electronic Materials. https://doi.org/10.1002/aelm.202500866
Vancouver
Daniels R, Wattad D, Ronen R, Saad D, Kvatinsky S. On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification. Advanced Electronic Materials. 2026. doi:10.1002/aelm.202500866
BibTeX
@article{Daniels2026,
author = {Daniels, Rishona and Wattad, Duna and Ronen, Ronny and Saad, David and Kvatinsky, Shahar},
title = {On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification},
journal = {Advanced Electronic Materials},
year = {2026},
doi = {10.1002/aelm.202500866}
}
EUVIMED