Memristive Reservoirs Learn to Learn

TL;DR

This paper demonstrates that memristive reservoirs can be optimized using a learn-to-learn framework, achieving brain-like dynamics and effective hyperparameter tuning, and can mimic neuronal membrane potentials for interfacing spike-based and continuous processes.

Contribution

It introduces a learn-to-learn approach for optimizing memristive reservoirs, revealing their potential for neuromorphic computing and neural interface applications.

Findings

Optimal hyperparameters found at the edge of formation of conductive pathways.

Reservoirs exhibit membrane potential behaviors similar to spiking neurons.

Systems can serve as interfaces between spike-based and continuous neural processes.

Abstract

Memristive reservoirs draw inspiration from a novel class of neuromorphic hardware known as nanowire networks. These systems display emergent brain-like dynamics, with optimal performance demonstrated at dynamical phase transitions. In these networks, a limited number of electrodes are available to modulate system dynamics, in contrast to the global controllability offered by neuromorphic hardware through random access memories. We demonstrate that the learn-to-learn framework can effectively address this challenge in the context of optimization. Using the framework, we successfully identify the optimal hyperparameters for the reservoir. This finding aligns with previous research, which suggests that the optimal performance of a memristive reservoir occurs at the `edge of formation' of a conductive pathway. Furthermore, our results show that these systems can mimic membrane potential behavior observed in spiking neurons, and may serve as an interface between spike-based and continuous processes.