Reservoir Computing with 3D Nanowire Networks

TL;DR

This study uses detailed simulations to compare 2D and quasi-3D nanowire networks in reservoir computing, revealing similar performance but greater resilience to noise in 3D structures, with implications for neuromorphic computing.

Contribution

It demonstrates that stacking nanowires in quasi-3D networks does not impair computational performance and enhances robustness, challenging prior assumptions about topology's role in RC.

Findings

Quasi-3D networks are more resilient to input noise.

Networks with fewer electrodes perform near optimal.

Topology has less impact on performance than previously thought.

Abstract

Networks of nanowires are currently being explored for a range of applications in brain-like (or neuromorphic) computing, and especially in reservoir computing (RC). Fabrication of real-world computing devices requires that the nanowires are deposited sequentially, leading to stacking of the wires on top of each other. However, most simulations of computational tasks using these systems treat the nanowires as 1D objects lying in a perfectly 2D plane - the effect of stacking on RC performance has not yet been established. Here we use detailed simulations to compare the performance of perfectly 2D and quasi-3D (stacked) networks of nanowires in two tasks: memory capacity and nonlinear transformation. We also show that our model of the junctions between nanowires is general enough to describe a wide range of memristive networks, and consider the impact of physically realistic electrode configurations on performance. We show that the various networks and configurations have a strikingly similar performance in RC tasks, which is surprising given their radically different topologies. Our results show that networks with an experimentally achievable number of electrodes perform close to the upper bounds achievable when using the information from every wire. However, we also show important differences, in particular that the quasi-3D networks are more resilient to changes in the input parameters, generalizing better to noisy training data. Since previous literature suggests that topology plays an important role in computing performance, these results may have important implications for future applications of nanowire networks in neuromorphic computing.