Abstract
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 (Formula presented.) classification accuracy on MNIST, comparable with the best reported memristor-based RC implementations. Furthermore, the method maintains high robustness under (Formula presented.) device variability, achieving an accuracy of up to (Formula presented.). 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.
| Original language | English |
|---|---|
| Article number | e00866 |
| Number of pages | 14 |
| Journal | Advanced Electronic Materials |
| Early online date | 4 May 2026 |
| DOIs | |
| Publication status | E-pub ahead of print - 4 May 2026 |
Bibliographical note
© 2026 The Author(s). Advanced Electronic Materials published by Wiley-VCH GmbH. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.Data Access Statement
The codes used for the simulations in this study are available on GitHub here: (https://github.com/rishonadaniels/On_the_role_of_preprocessing_and_memristor_dynamics_in_reservoir_computing)Funding
This research has been partially funded by the European Union’s Horizon 2020 Research And Innovation Programme FET-Open NEU-Chip under grant agreement No. 964877 and funded by the European Union (ERC, Real-Database-PIM, 101157452).
| Funders | Funder number |
|---|---|
| European Commission | |
| Horizon 2020 Framework Programme | 964877 |
| European Research Council | 101157452 |
Keywords
- reservoir computing
- volatile memristors
- neuromorphic computing
Fingerprint
Dive into the research topics of 'On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver