Hierarchical Composition of Memristive Networks for Real-Time Computing

TL;DR

This paper proposes a hierarchical approach to composing memristive networks into larger reservoirs, enhancing real-time computing capabilities and outperforming monolithic networks on waveform and complex tasks.

Contribution

It introduces a hierarchical composition method for memristive networks that reduces signal correlation and improves computational performance in reservoir computing.

Findings

Hierarchical composition outperforms monolithic networks by at least 20% on waveform tasks.

Reduces error by up to a factor of 2 on NARMA-10 task.

Single memristive networks cannot produce correct results on complex tasks.

Abstract

Advances in materials science have led to physical instantiations of self-assembled networks of memristive devices and demonstrations of their computational capability through reservoir computing. Reservoir computing is an approach that takes advantage of collective system dynamics for real-time computing. A dynamical system, called a reservoir, is excited with a time-varying signal and observations of its states are used to reconstruct a desired output signal. However, such a monolithic assembly limits the computational power due to signal interdependency and the resulting correlated readouts. Here, we introduce an approach that hierarchically composes a set of interconnected memristive networks into a larger reservoir. We use signal amplification and restoration to reduce reservoir state correlation, which improves the feature extraction from the input signals. Using the same number of output signals, such a hierarchical composition of heterogeneous small networks outperforms monolithic memristive networks by at least 20% on waveform generation tasks. On the NARMA-10 task, we reduce the error by up to a factor of 2 compared to homogeneous reservoirs with sigmoidal neurons, whereas single memristive networks are unable to produce the correct result. Hierarchical composition is key for solving more complex tasks with such novel nano-scale hardware.