Neuromorphic nanocluster networks: Critical role of the substrate in nano-link formation

Abstract

Atomic cluster-based networks represent a promising architecture for the realization of neuromorphic computing systems, which may overcome some of the limitations of the current computing paradigm. The formation and breakage of links between the clusters are of utmost importance for the functioning of these computing systems. This paper reports the results of molecular dynamics simulations of synapse (bridge) formation at elevated temperature and thermal breaking processes between 2.8 nm-sized Au1415 clusters deposited on a carbon substrate, a model system. Crucially, we find that the bridge formation process is driven by the diffusion of gold atoms along the substrate, no matter how small the gap between the clusters themselves. The complementary simulations of the bridge breaking process reveal the existence of a threshold bias voltage to activate bridge rupture via Joule heating. These results provide an atomistic-level understanding of the fundamental dynamical processes occurring in neuromorphic cluster arrays.

Self-Organized Memristive Ensembles of Nanoparticles Below the Percolation Threshold: Switching Dynamics and Phase Field Description

“…Recent results of molecular dynamics modeling of filaments, including taking into account the graphite substrate, are given in the works [ 17 , 29 ]. The formation of sufficiently wide filaments during the functioning of the memristive network can contribute to the subsequent coalescence of nanoparticles, i.e., the nanobridge does not break: it pulls the nanoparticles together [ 30 ].…”