AlOx-based resistive switching device with gradual resistance modulation for neuromorphic device application

Yi Wu, Shimeng Yu, H. S.Philip Wong, Yu Sheng Chen, Heng Yuan Lee, Sum Min Wang, Pei Yi Gu, Frederick Chen, Ming Jinn Tsai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

29 Scopus citations

Abstract

AlOx-based resistive switching device (RRAM) with multi-level storage capability was investigated for the potential to serve as an electronic synapse device. The Ti/AlOx/TiN memory stack with memory size 0.48umx0.48um was fabricated; the resistive layer AlOx was deposited using atomic-layer- deposition (ALD) method. Multi-level resistance states were obtained by varying the compliance current levels or the applied voltage amplitudes during pulse cycling. These resistance states are thermally stable for over 1E5s at 125oC. The memory cell resistance can be continuously increased or decreased from each pulse cycle to pulse cycle. More than 1E5 endurance cycles and reading cycles were demonstrated. We further study the potential using this AlOx-based RRAM as electronic synapse device. Around 1% resistance change per pulse cycling was achieved and a plasticity learning rule pulse scheme was proposed to implement the memory device in large-scale hardware neuromorphic computing system.

Original languageEnglish (US)
Title of host publication2012 4th IEEE International Memory Workshop, IMW 2012
DOIs
StatePublished - 2012
Event2012 4th IEEE International Memory Workshop, IMW 2012 - Milano, Italy
Duration: May 20 2012May 23 2012

Publication series

Name2012 4th IEEE International Memory Workshop, IMW 2012

Other

Other2012 4th IEEE International Memory Workshop, IMW 2012
CountryItaly
CityMilano
Period5/20/125/23/12

Keywords

  • AlOx
  • RRAM
  • neuromorphic computation
  • resistive switching memory
  • synapse

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'AlOx-based resistive switching device with gradual resistance modulation for neuromorphic device application'. Together they form a unique fingerprint.

Cite this