Premium
Memristive Neural Networks: Zeolite‐Based Memristive Synapse with Ultralow Sub‐10‐fJ Energy Consumption for Neuromorphic Computation (Small 13/2021)
Author(s) -
Zeng Tao,
Zou Xiaoqin,
Wang Zhongqiang,
Yu Guangli,
Yang Zhi,
Rong Huazhen,
Zhang Chi,
Xu Haiyang,
Lin Ya,
Zhao Xiaoning,
Ma Jiangang,
Zhu Guangshan,
Liu Yichun
Publication year - 2021
Publication title -
small
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.785
H-Index - 236
eISSN - 1613-6829
pISSN - 1613-6810
DOI - 10.1002/smll.202170057
Subject(s) - neuromorphic engineering , synapse , artificial neural network , zeolite , memristor , energy consumption , computation , synaptic weight , materials science , computer science , energy (signal processing) , nanotechnology , models of neural computation , neuroscience , artificial intelligence , chemistry , electronic engineering , physics , electrical engineering , engineering , psychology , algorithm , biochemistry , quantum mechanics , catalysis
In article number 2006662, Zhongqiang Wang, Haiyang Xu, Guangshan Zhu, and co‐workers report a zeolite‐based memristive synapse with an ultralow energy consumption of sub‐10 fJ per synaptic spike. Several essential synaptic learning and memory functions are demonstrated in such zeolite‐based memristive synapse by electrical and chemical methods, which facilitates the development of highly efficient memristive neural networks.