Memristor’s characteristics: From non-ideal to ideal  

作　　者：孙帆 粟静 李杰 段书凯 胡小方 Fan Sun;Jing Su;Jie Li;Shukai Duan;Xiaofang Hu(College of Artificial Intelligence,Southwest University,Chongqing 400715,China)

机构地区：[1]College of Artificial Intelligence,Southwest University,Chongqing 400715,China

出　　处：《Chinese Physics B》2023年第2期504-508,共5页中国物理B（英文版）

基　　金：supported by the National Natural Science Foundation of China (Grant Nos. 61976246 and U20A20227);the Natural Science Foundation of Chongqing, China (Grant No. cstc2020jcyj-msxm X0385);the National Key R&D Program of China (Grant Nos. 2018YFB130660 and 2018YFB1306604)。

摘　　要：Memristor has been widely studied in the field of neuromorphic computing and is considered to be a strong candidate to break the von Neumann bottleneck. However, the non-ideal characteristics of memristor seriously limit its practical application. There are two sides to everything, and memristors are no exception. The non-ideal characteristics of memristors may become ideal in some applications. Genetic algorithm(GA) is a method to search for the optimal solution by simulating the process of biological evolution. It is widely used in the fields of machine learning, combinatorial optimization,and signal processing. In this paper, we simulate the biological evolutionary behavior in GA by using the non-ideal characteristics of memristors, based on which we design peripheral circuits and path planning algorithms based on memristor networks. The experimental results show that the non-ideal characteristics of memristor can well simulate the biological evolution behavior in GA.

关 键 词：MEMRISTOR non-ideal characteristic genetic algorithm path planning 

分 类 号：TN60[电子电信—电路与系统]