完整後設資料紀錄
DC 欄位語言
dc.contributor.authorWu, Tzu-Yunen_US
dc.contributor.authorHuang, Hsin-Huien_US
dc.contributor.authorChu, Yueh-Huaen_US
dc.contributor.authorChang, Chih-Chengen_US
dc.contributor.authorWu, Ming -Hungen_US
dc.contributor.authorHsu, Chien-Huaen_US
dc.contributor.authorWu, Chien -Tingen_US
dc.contributor.authorWu, Min-Cien_US
dc.contributor.authorWu, Wen-Weien_US
dc.contributor.authorChang, Tian-Sheuanen_US
dc.contributor.authorLee, Heng-Yuanen_US
dc.contributor.authorSheu, Shyh-Shyuanen_US
dc.contributor.authorLot, Wei-Chungen_US
dc.contributor.authorHou, Tuo-Hungen_US
dc.date.accessioned2020-10-05T02:01:28Z-
dc.date.available2020-10-05T02:01:28Z-
dc.date.issued2019-01-01en_US
dc.identifier.isbn978-1-7281-4031-5en_US
dc.identifier.issn2380-9248en_US
dc.identifier.urihttp://hdl.handle.net/11536/155252-
dc.description.abstractThis paper presents a unique opportunity of HZO ferroelectric tunnel junction (FTJ) for in-memory computing. The device operates at an extremely low sub-nA current while simultaneously achieving 50-ns fast switching, > 10(7) cycling endurance, > 10-yr retention, minimal variability, and analog state modulation. We analyze an FTJ-based deep binary neural network. It achieves better accuracy and remarkable 702, 101, and 7 x 10(4) times improvements in power, area, and energy area product efficiency compared with those using NVMs with a typical mu A cell current designed for fast memory access.en_US
dc.language.isoen_USen_US
dc.titleSub-nA Low-Current HZO Ferroelectric Tunnel Junction for High-Performance and Accurate Deep Learning Accelerationen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2019 IEEE INTERNATIONAL ELECTRON DEVICES MEETING (IEDM)en_US
dc.citation.spage0en_US
dc.citation.epage0en_US
dc.contributor.department材料科學與工程學系zh_TW
dc.contributor.department電子工程學系及電子研究所zh_TW
dc.contributor.departmentDepartment of Materials Science and Engineeringen_US
dc.contributor.departmentDepartment of Electronics Engineering and Institute of Electronicsen_US
dc.identifier.wosnumberWOS:000553550000133en_US
dc.citation.woscount0en_US
顯示於類別:會議論文