Research progress of neuromorphic computation based on memcapacitors
-
Published:2021
Issue:7
Volume:70
Page:078701
-
ISSN:1000-3290
-
Container-title:Acta Physica Sinica
-
language:
-
Short-container-title:Acta Phys. Sin.
Author:
Ren Kuan,Zhang Ke-Jia,Qin Xi-Zi,Ren Huan-Xin,Zhu Shou-Hui,Yang Feng,Sun Bai,Zhao Yong,Zhang Yong, , , , ,
Abstract
The rapid development of artificial intelligence (AI) requires one to speed up the development of the domain-specific hardware specifically designed for AI applications. The neuromorphic computing architecture consisting of synapses and neurons, which is inspired by the integrated storage and parallel processing of human brain, can effectively reduce the energy consumption of artificial intelligence in computing work. Memory components have shown great application value in the hardware implementation of neuromorphic computing. Compared with traditional devices, the memristors used to construct synapses and neurons can greatly reduce computing energy consumption. However, in neural networks based on memristors, updating and reading operations have system energy loss caused by voltage and current of memristors. As a derivative of memristor, memcapacitor is considered as a potential device to realize a low energy consumption neural network, which has attracted wide attention from academia and industry. Here, we review the latest advances in physical/simulated memcapacitors and their applications in neuromorphic computation, including the current principle and characteristics of physical/simulated memcapacitor, representative synapses, neurons and neuromorphic computing architecture based on memcapacitors. We also provide a forward-looking perspective on the opportunities and challenges of neuromorphic computation based on memcapacitors.
Publisher
Acta Physica Sinica, Chinese Physical Society and Institute of Physics, Chinese Academy of Sciences
Subject
General Physics and Astronomy
Reference72 articles.
1. Goodfellow I, Bengio Y, Courville A 2016 Deep Learning (Cambridge: The MIT Press) pp1−100 2. James C D, Aimone J B, Miner N E, Vineyard C M, Rothganger F H, Carlson K D, Mulder S A, Draelos T J, Faust A, Marinella M J, Naegle J H, Plimpton S J 2017 Biol. Inspired Cogn. Archit. 19 49 3. Merolla P A, Arthur J V, Alvarez-Icaza R, Cassidy A S, Sawada J, Akopyan F, Jackson B L, Imam N, Guo C, Nakamura Y, Brezzo B, Vo I, Esser S K, Appuswamy R, Taba B, Amir A, Flickner M D, Risk W P, Manohar R, Modha D S 2014 Science 345 668 4. Furber S B, Galluppi F, Temple S, Plana L A 2014 Proc. IEEE 102 652 5. Chua L 1971 IEEE Trans. Circuit Theory 18 507
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|