All-solid-state Ion Doping Synaptic Transistor for Bionic Neural computing

Q. N. Wang, C. Zhao, W. Liu, H. Van Zalinge, Y. N. Liu, L. Yang, C. Z. Zhao

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

1 Citation (Scopus)

Abstract

Artificial synapses are the critical component for low-power neuromorphic computing, which surpasses the limitations of von Neumann's structure. Compared with two-terminal memristors and three-terminal transistors with wire formation and charge trapping mechanisms, the emerging electrolytic gated transistor (EGT) has proven to be a promising neuromorphic application due to its outstanding analog switching performance. Candidate. This paper presents a new low-temperature solution-based oxide thin film transistor, which uses an ion-doped dielectric layer. The device also has a low-noise linear conductance update and a relatively high Gmax/Gmin. The realization of ANN neuromorphic calculation has nearly ideal accuracy. These results highlight the potential of EGT based on AlOx-Li/InOx thin-film transistors in the next generation of low-power electronics outside of the von Neumann architecture.

Original languageEnglish
Title of host publication2021 International Conference on IC Design and Technology, ICICDT 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665449984
DOIs
Publication statusPublished - 2021
Event2021 International Conference on IC Design and Technology, ICICDT 2021 - Dresden, Germany
Duration: 15 Sept 202117 Sept 2021

Publication series

Name2021 International Conference on IC Design and Technology, ICICDT 2021

Conference

Conference2021 International Conference on IC Design and Technology, ICICDT 2021
Country/TerritoryGermany
CityDresden
Period15/09/2117/09/21

Keywords

  • MNIST
  • neural computing
  • solution-processed transistor
  • synaptic device

Cite this