Nonlinear Autoregression with Convergent Dynamics on Novel Computational Platforms

TL;DR

This paper presents reservoir computing models with output feedback as nonlinear autoregressive systems, demonstrating their effectiveness in modeling complex data and potential for control, using classical and quantum platforms.

Contribution

It introduces reservoir computers with output feedback as stationary nonlinear autoregressive models, expanding their application to classical and quantum systems for data modeling and control.

Findings

Reservoir computers effectively model synthetic and real data.

Quantum reservoir computers show promise for complex data modeling.

The approach offers potential for control applications.

Abstract

Nonlinear stochastic modeling is useful for describing complex engineering systems. Meanwhile, neuromorphic (brain-inspired) computing paradigms are developing to tackle tasks that are challenging and resource intensive on digital computers. An emerging scheme is reservoir computing which exploits nonlinear dynamical systems for temporal information processing. This paper introduces reservoir computers with output feedback as stationary and ergodic infinite-order nonlinear autoregressive models. We highlight the versatility of this approach by employing classical and quantum reservoir computers to model synthetic and real data sets, further exploring their potential for control applications.