摘要
Doped HfO2 Ferroelectric Field-Effect Transistors (FeFETs), which enable a low power operation, multilevel states tunability, and CMOS process compatibility , are promising candidates for neuro-inspired computing [1]. Currently, the 32 levels of conductance states under the neuromorphic computing in Zr-doped FeFETs and MOSCAPs have been successfully demonstrated [2]. In this work, Si-doped HfO2 FeFETs are fabricated and characterized, showing a promising neuromorphic functionalities with up to 64-states and large dynamic range Furthermore, two different pulsing schemes are used for extracting the device-level neuromorphic functionalities, suggesting that the programming pulses significantly influence the neuromorphic performance of the device.
原文 | English |
---|---|
頁數 | 2 |
DOIs | |
出版狀態 | Published - 4月 2022 |
事件 | 2022 International Symposium on VLSI Technology, Systems and Applications, VLSI-TSA 2022 - Hsinchu, 台灣 持續時間: 18 4月 2022 → 21 4月 2022 |
Conference
Conference | 2022 International Symposium on VLSI Technology, Systems and Applications, VLSI-TSA 2022 |
---|---|
國家/地區 | 台灣 |
城市 | Hsinchu |
期間 | 18/04/22 → 21/04/22 |