Emerging memristive artificial neuron and synapse devices for the neuromorphic electronics era

• Main Authors: Li, Jiayi, Abbas, Haider, Ang, Diing Shenp, Ali, Asif, Ju, Xin
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Electrical and electronic engineering::Microelectronics; Artificial Intelligence; Deep Neural Network
• Online Access: https://hdl.handle.net/10356/169872
• Institution: Nanyang Technological University

Growth of data eases the way to access the world but consumes increasing energy to store and process. Neuromorphic electronics emerged in the last decade, inspired by biological neuron and synapses, with in-memory computing ability, extenuates the ‘von Neumann bottleneck’ between memory and processor, offers a promising solution to reduce the efforts both in data storage and process thanks to their multi-bit non-volatility, biological-emulated characteristics, and silicon compatibility. This work reviews the recent advances of emerging memristive devices for artificial neuron and synapse applications, including memory and data-processing ability: The physics and characteristics are discussed first, i.e., valance changing, electrochemical metallization, phase changing, interfaced-controlling, charge-trapping, ferroelectric tunnelling, and spin-transfer torquing. Next, we propose a universal benchmark for the artificial synapse devices on spiking energy consumption, standby power consumption, and spike timing. Based on the benchmark, we address the challenges, suggest the guidelines for intra-device and inter-device design, and outlook the neuromorphic applications for the resistive switching-based artificial neuron and synapse devices.