Traditional recurrent neural networks are composed of capacitors, inductors, resistors, and operational amplifiers.Memristive neural networks are constructed by replacing resistors with memristors. This paper focuses on the memory analysis,i.e. the initial value computation, of memristors. Firstly, we present the memory analysis for a single memristor based on memristors’ mathematical models with linear and nonlinear drift.Secondly, we present the memory analysis for two memristors in series and... 

【文章來源】：IEEE/CAA Journal of Automatica Sinica. 2020,7(01)EISCICSCD

【文章頁數(shù)】：10 頁

【參考文獻】：
期刊論文
[1]憶阻及其應(yīng)用研究綜述[J]. 王小平,沈軼,吳計生,孫軍偉,李薇.  自動化學(xué)報. 2013(08)



本文編號：3386646