Additive manufacture of polymeric organometallic ferroelectric diodes (POMFeDs) for structural neuromorphic hardware

Abstract

Hardware design and implementation for online machine learning applications is complicated by a number of facets of conventional artificial neural networks (ANN), e.g. deep neural networks (DNNs), such as reliance on atemporal locality, offline learning using large datasets, potential difficulties in transfer from model to substrates, and issues with processing of noisy sensory data using energy-efficient and asynchronous information processing modalities. Analog or mixed-signal spiking neural networks (SNNs) have promise for lower power, temporally localised, and stimuli selective sensing and inference but are difficult fabricate at low cost. Investigation of beyond-CMOS alternative organic substrates may be worthwhile for development of unconventional neuromorphic hardware with pseudo-spiking dynamics for structural electronics integration in bio-signal processing and robotics. Here, polymeric organometallic ferroelectric diodes (POMFeDs) are introduced for development of printable ferroelectric in-sensor SNNs.