Power-Efficient Multisensory Reservoir Computing Based on Zr-doped HfO 2 Memcapacitive Synapse Arrays.

Hardware implementations tailored to requirements in reservoir computing would facilitate lightweight and powerful temporal processing. Capacitive reservoirs would boost power efficiency due to their ultralow static power consumption but haven't been experimentally exploited yet. Here we report an oxide-based memcapacitive synapse (OMC) based on Zr-doped HfO 2 (HZO) for a power-efficient and multisensory processing reservoir computing system. The nonlinearity and state richness required for reservoir computing could be originated from the capacitively coupled polarization switching and charge trapping of hafnium oxide-based devices. The power consumption (∼113.4 fJ/spike) and temporal processing versatility outperform most resistive reservoirs. Our system has been verified by common benchmark tasks, and it exhibits high accuracy (>94%) in recognizing multisensory information, including acoustic, electrophysiological, and mechanic modalities. As a proof-of-concept, a touchless user interface for virtual shopping is demonstrated based on our OMC-based reservoir computing system, benefiting from its interference-robust acoustic and electrophysiological perception. Our results would shed light on the development of high power-efficient human-machine interfaces and machine-learning platforms. This article is protected by copyright. All rights reserved.