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

2026-04-23

AI Summary

This work addresses the performance limitations of reservoir computing for image classification imposed by non-ideal memristor characteristics—such as conductance decay, quantization error, and device-to-device variability—and proposes a parallel delayed feedback network architecture based on volatile memristors, augmented with an input preprocessing strategy to enhance information encoding. The study elucidates the intrinsic relationship between memristor dynamics and reservoir performance and demonstrates system robustness through comprehensive modeling of device variability. Evaluated on the MNIST dataset, the proposed approach achieves a classification accuracy of 95.89%, maintaining a high accuracy of 94.2% even under 20% device variability, thereby achieving an effective balance between performance and robustness.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Learning & Optimization for CV
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

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 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.

Problem

• reservoir computing
• memristor dynamics
• image classification
• device variability
• volatile memristors

Innovation

• Reservoir Computing
• Memristor Dynamics
• Preprocessing
• Volatile Memristors
• Image Classification