Essential Characteristics of Memristors for Neuromorphic Computing. (25th October 2022)

• Record Type: Journal Article
• Authors: Chen, Wenbin; Song, Lekai; Wang, Shengbo; Zhang, Zhiyuan; Wang, Guanyu; Hu, Guohua; Gao, Shuo
• Is Part Of: Advanced Electronic Materials. Volume 9:Number 2(2023)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-10-25
• Subjects: memristors -- neural networks -- neuromorphic computing -- reliability -- variability; Materials -- Electric properties -- Periodicals; Materials science -- Periodicals; Magnetic materials -- Periodicals; Electronic apparatus and appliances -- Periodicals; 537
• DOI: 10.1002/aelm.202200833
• Languages: English
• ISSNs: 2199-160X

Abstract

Abstract: The memristor is a resistive switch where its resistive state is programable based on the applied voltage or current. Memristive devices are thus capable of storing and computing information simultaneously, breaking the Von Neumann bottleneck. Since the first nanomemristor made by Hewlett‐Packard in 2008, advances so far have enabled nanostructured, low‐power, high‐durability devices that exhibit superior performance over conventional CMOS devices. Herein, the development of memristors based on different physical mechanisms is reviewed. In particular, device stability, integration density, power consumption, switching speed, retention, and endurance of memristors, that are crucial for neuromorphic computing, are discussed in detail. An overview of various neural networks with a focus on building a memristor‐based spike neural network neuromorphic computing system is then provided. Finally, the existing issues and challenges in implementing such neuromorphic computing systems are analyzed, and an outlook for brain‐like computing is proposed. Abstract : Neuromorphic computing (NC) is approaching, and memristor technology is treated as powerful support during the journey. In this article, for a deeper understanding of how to implement NC by memristors, the authors first review and explain essential characteristics of memristors from mechanisms to applications, and then discuss current challenges preventing achieving expected NC.