# On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification

arXiv: https://arxiv.org/abs/2604.21602 · HTML: https://mlsanity.com/paper/2604.21602/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 50 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 6 of 6)

- [Physical Reservoir Computing with Origami and its Application to Robotic Crawling](https://mlsanity.com/paper/2101.08348/) (2021)
- [High Speed Human Action Recognition using a Photonic Reservoir Computer](https://mlsanity.com/paper/2305.15283/) (2023)
- [Hopf Physical Reservoir Computer for Reconfigurable Sound Recognition](https://mlsanity.com/paper/2212.10370/) (2022)
- [Multifunctional physical reservoir computing in soft tensegrity robots](https://mlsanity.com/paper/2507.21496/) (2025)
- [VVTEAM: A Compact Behavioral Model for Volatile Memristors](https://mlsanity.com/paper/2409.17723/) (2024)
- [Preprocessing Methods for Memristive Reservoir Computing for Image Recognition](https://mlsanity.com/paper/2506.05588/) (2025)

## Abstract (arXiv)

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 95.89% classification accuracy on MNIST, comparable with the best reported memristor-based RC implementations. Furthermore, the method maintains high robustness under 20% device variability, achieving an accuracy of up to 94.2%. 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.