In materia reservoir computing with a fully memristive architecture based on self-organizing nanowire networks
Recently published on Nature Materials a study on in materia reservoir computing in a fully memristive architecture based on self-organized nanowire networks. The work has been developed by INRiM - Istituto Nazionale di Ricerca Metrologica, Politecnico di Torino e Politecnico di Milano, with the support of the European project MEMQuD.
📌 Thanks to short-term memory and functional synaptic connectivity with nonlinear dynamics of designless nanowire networks combined with long-term memory of ReRam devices, this brain-inspired architecture allows neuromorphic-type of data processing and implementation of reservoir computing.
👉 The research demonstrated that the emergent memristive behaviour of nanowire networks allows in materia implementation of brain-inspired computing paradigms characterized by a reduced training cost.
📚 Read the paper “In materia reservoir computing with a fully memristive architecture based on self-organizing nanowire network”, click the link: https://rdcu.be/cyMvg