Scalable Memristive-Friendly Reservoir Computing for Time Series Classification

TL;DR

This paper introduces MARS, a scalable, memristive-friendly reservoir computing architecture that significantly accelerates training and improves performance on time series classification tasks.

Contribution

The paper proposes MARS, a novel parallel reservoir architecture with skip connections, achieving up to 21x faster training and better accuracy than existing models.

Findings

MARS outperforms gradient-based models like LRU, S5, and Mamba on long sequence benchmarks.

Training time is reduced from minutes/hours to seconds or hundreds of milliseconds.

MARS enables scalable, energy-efficient neuromorphic learning systems.

Abstract

Memristive devices present a promising foundation for next-generation information processing by combining memory and computation within a single physical substrate. This unique characteristic enables efficient, fast, and adaptive computing, particularly well suited for deep learning applications. Among recent developments, the memristive-friendly echo state network (MF-ESN) has emerged as a promising approach that combines memristive-inspired dynamics with the training simplicity of reservoir computing, where only the readout layer is learned. Building on this framework, we propose memristive-friendly parallelized reservoirs (MARS), a simplified yet more effective architecture that enables efficient scalable parallel computation and deeper model composition through novel subtractive skip connections. This design yields two key advantages: substantial training speedups of up to 21x over the inherently lightweight echo state network baseline and significantly improved predictive performance. Moreover, MARS demonstrates what is possible with parallel memristive-friendly reservoir computing: on several long sequence benchmarks our compact gradient-free models substantially outperform strong gradient-based sequence models such as LRU, S5, and Mamba, while reducing full training time from minutes or hours down seconds or even only a few hundred milliseconds. Our work positions parallel memristive-friendly computing as a promising route towards scalable neuromorphic learning systems that combine high predictive capability with radically improved computational efficiency, while providing a clear pathway to energy-efficient, low-latency implementations on emerging memristive and in-memory hardware.