Machine learning compact device models applied to optoelectronic memristor

Albert Lin, Tejender Rawat, Ming Hsien Hsu, Chung Yuan Chang, Han Chun Tung, Tseung Yuen Tseng

研究成果: Conference contribution同行評審

摘要

Machine learning compact device models (CM) have emerged as an alternative to physical CMs in terms of high flexibility and short development time. Based on our previous effort (Tran. Elec. Dev. Vol. 69, p1835), we have applied the same approach to optoelectronic memristors, and the flexibility of ML CMs is observed. The python/Tensorflow model is constructed to fit the devices, and Verilog-A and HSPICE are used for circuits. The fitting mean square error is 2.816 times 10{-12}} A2 in current and 0.00157 in the state, and a set-read-reset-read cycles in circuits in the dark and under illumination are demonstrated.

原文English
主出版物標題2022 IEEE Photonics Conference, IPC 2022 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781665434874
DOIs
出版狀態Published - 2022
事件2022 IEEE Photonics Conference, IPC 2022 - Vancouver, 加拿大
持續時間: 13 11月 202217 11月 2022

出版系列

名字2022 IEEE Photonics Conference, IPC 2022 - Proceedings

Conference

Conference2022 IEEE Photonics Conference, IPC 2022
國家/地區加拿大
城市Vancouver
期間13/11/2217/11/22

指紋

深入研究「Machine learning compact device models applied to optoelectronic memristor」主題。共同形成了獨特的指紋。

引用此