CMOS-Compatible Low-Power Gated Diode Synaptic Device for Hardware- Based Neural Network

  • Min Kyu Park
  • , Ho Nam Yoo
  • , Joon Hwang
  • , Sung Yun Woo
  • , Dongseok Kwon
  • , Young Tak Seo
  • , Jong Ho Lee
  • , Jong Ho Bae

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

A gated diode with a charge trap insulator stack (Al2O3/Si3N4/SiO2) is proposed as a synaptic device and its potentiation and depression operations have been demonstrated. Using the band-to-band tunneling current, the gated diode operates with low current (in nanoampere range) and is suitable for low-power hardware-based neural networks. Since the proposed device has merits on simple and compact structure (half of a MOSFET) and compatibility with conventional CMOS technology, integration with CMOS peripheral circuits including neuron circuits and driving IC is possible.

Original languageEnglish
Pages (from-to)832-837
Number of pages6
JournalIEEE Transactions on Electron Devices
Volume69
Issue number2
DOIs
StatePublished - 1 Feb 2022

Keywords

  • Band-to-band current
  • charge trap memory
  • low power
  • synaptic device

Fingerprint

Dive into the research topics of 'CMOS-Compatible Low-Power Gated Diode Synaptic Device for Hardware- Based Neural Network'. Together they form a unique fingerprint.

Cite this