Memristive Reservoirs Learn to Learn
This work addresses optimization for neuromorphic hardware, but it is incremental as it builds on prior knowledge about optimal performance in memristive systems.
The paper tackled the challenge of optimizing memristive reservoirs, which have limited electrode controllability, by applying a learn-to-learn framework to identify optimal hyperparameters, resulting in performance aligned with the 'edge of formation' of conductive pathways and enabling mimicry of spiking neuron behavior.
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.