Forgetting memristors and memristor bridge synapses with long- and short-term memories

作     者：Chen, Ling Zhou, Wenhao Li, Chuandong Huang, Junjian 

作者机构：Southwest Univ Coll Elect Informat & Engn Chongqing Key Lab Nonlinear Circuits & Intelligen Chongqing 400715 Peoples R China 

出 版 物：《NEUROCOMPUTING》 (神经计算)

年 卷 期：2021年第456卷

页      面：126-135页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Key Research and Development Project [2018AAA0100101] Natural Science Foundation of China [61633011, 61702066, 61873213, 11747125, 61503307] Fundamental Research Funds for the Central Universities [XDJK2019B009, SWU020005] Chongqing Research Program of Basic Research and Frontier techno-logical Science Foundation [cstc2017jcyjAX0256, cstc2018jcyjAX0810] Chongqing Key Laboratory of Mobile Communications Technology [cquptmct202002] 

主　　题：Forgetting memristor Long short-term memory Synapse Memristor bridge 

摘      要：In this paper, an ideal current source forgetting memristor model is proposed. Based on the model, three kinds of synapses with long-and short-term memory are designed: the series forgetting memristor synapse, the forgetting memristor bridge synapse written independently and the forgetting memristor bridge synapse written in batches. Combined with the forgetting property, the long-and short-term weight of the forgetting synapse can be controlled by the long-and short-term resistance of memristors. Compared the three forgetting synapses, the series forgetting memristor synapse has the lowest requirement for memristors, the forgetting memristor bridge synapse written independently is the most flexible, and the forgetting memristor bridge synapse written in batches is the most convenient. Compared with traditional synapses, forgetting synapses with long-and short-term memory have multi-weight storage. When forgetting synapses are applied to associative memory, it can be found more patterns are stored in the neural network and different patterns are recalled at different time due to the forgetting effect. (c) 2021 Elsevier B.V. All rights reserved.