Enhanced Linearity in CBRAM Synapse by Post Oxide Deposition Annealing for Neuromorphic Computing Applications

Chun Ling Hsu, Aftab Saleem, Amit Singh, Dayanand Kumar, Tseung-Yuen Tseng

Research output: Contribution to journalArticlepeer-review

26 Scopus citations


Artificial synapse with good linearity is a critical issue in conductive bridging random access memory (CBRAM) synaptic device to accomplish an efficient learning approach in the artificial intelligence system. In this work, we investigate a novel approach to enhance the linearity of CBRAM synapse. The linearity of a memristive synapse can be improved by the high-temperature vacuum annealing process. The annealed device not only improves reliability such as endurance characteristics but also improves the synaptic characteristics including multilevel characteristics with varying RESET stop voltages from -0.60 to -1.40 V. The nonlinearities of potentiation and depression are 1.36 and -2.18 with 500 conductance pulses, respectively, and the device exhibits 720 training epochs with a total number of 720,000 pulse numbers. The post oxide annealed CBRAM device with analog switching behavior and excellent reliability is potential to be an artificial synapse for neuromorphic computing. In addition, the experimental potentiation and depression data are employed to train HNN for image processing of 30 x 30 pixels comprising 900 synapses. It is found that the HNN can be successfully trained to recognize the input image with a training accuracy of ~98% in 18 iterations.

Original languageEnglish
Pages (from-to)5578-5584
Number of pages7
JournalIEEE Transactions on Electron Devices
Issue number11
StatePublished - Nov 2021


  • Annealing
  • Artificial synapse
  • conductive bridging random access memory (CBRAM)
  • conductive filament (CF)
  • Depression
  • Hafnium oxide
  • Hopfield neural network
  • Linearity
  • memristor.
  • Switches
  • Synapses
  • Tin


Dive into the research topics of 'Enhanced Linearity in CBRAM Synapse by Post Oxide Deposition Annealing for Neuromorphic Computing Applications'. Together they form a unique fingerprint.

Cite this