Modular quantum extreme reservoir computing

TL;DR

This paper investigates how minimal inter-module connections in modular quantum reservoir computing can achieve performance comparable to single reservoirs, highlighting the importance of connectivity and entanglement for effective quantum machine learning.

Contribution

It systematically analyzes the impact of inter-module connections and entanglement in modular quantum reservoirs, demonstrating that few well-placed links suffice for high performance across datasets.

Findings

Few inter-module connections match single-reservoir accuracy.

Performance improves with increased inter-module entanglement.

Modular architecture applies to diverse datasets and reservoir types.

Abstract

Quantum reservoir computing employs fixed quantum dynamics as a feature map for machine learning. Integrating multiple quantum reservoirs, however, raises a key question: how few inter-module connections are sufficient to match the performance of a single reservoir? To address this, we explicitly separate intra-module dynamics from inter-module couplings and systematically examine different connectivity schemes. We find that even a small number of well-placed connections between two modules can match single-reservoir accuracy, with simple one-to-one connections proving highly effective. Performance generally improves with increasing inter-module entanglement, and these correlations persist for both $ZZ$-coupled and random modular reservoirs. Extensions to three modules and evaluations across multiple datasets (MNIST, Fashion-MNIST, CIFAR-10) suggest that the modular architecture can be applied to diverse reservoir types and image-classification datasets. These results motivate modular quantum reservoir designs that align naturally with realistic hardware, such as two-dimensional quantum-chip layouts or networks of small integrated quantum systems.