Spectral dynamics reservoir computing for high-speed hardware-efficient neuromorphic processing

TL;DR

This paper introduces spectral dynamics reservoir computing (SDRC), a novel framework that leverages spectral properties of physical systems for high-speed, hardware-efficient neuromorphic processing, demonstrated with spin waves and benchmark tasks.

Contribution

The paper presents SDRC, a new approach that uses analogue filtering and envelope detection to exploit spectral dynamics, enabling high-performance reservoir computing with minimal hardware complexity.

Findings

Achieves state-of-the-art performance with only 56 nodes

Demonstrates 98.0% accuracy on speech recognition

Effective for benchmark tasks like parity-check and nonlinear autoregressive models

Abstract

Physical reservoir computing (PRC) is a promising brain-inspired computing architecture for overcoming the von Neumann bottleneck by utilizing the intrinsic dynamics of physical systems. However, a major obstacle to its real-world implementation lies in the tension between extracting sufficient information for high computational performance and maintaining a hardware-feasible, high-speed architecture. Here, we report spectral dynamics reservoir computing (SDRC), a broadly applicable framework based on analogue filtering and envelope detection that bridges this gap. SDRC effectively exploits the fast spectral dynamics embedded in short-time, coarse spectra of material responses to attain strong computational capability while maintaining high-speed processing and minimal hardware overhead. This approach circumvents the need for implementation-intensive, precision-sensitive integrated circuits required in high-speed time-multiplexing measurements, while enabling real-time use of the material's spectral manifold as a high-dimensional computational resource. We implement and experimentally demonstrate SDRC applied to spin waves that achieves state-of-the-art-level performance with only 56 nodes on benchmark tasks of parity-check and second-order nonlinear autoregressive moving average, as well as high accuracy of 98.0% on a real-world problem of speech recognition.