A Learning-Rate Modulable and Reliable TiOx Memristor Array for Robust, Fast, and Accurate Neuromorphic Computing

Jingon Jang, Sanggyun Gi, Injune Yeo, Sanghyeon Choi, Seonghoon Jang, Seonggil Ham, Byunggeun Lee, Gunuk Wang

Research output: Contribution to journalArticlepeer-review

19 Citations (Scopus)

Abstract

Realization of memristor-based neuromorphic hardware system is important to achieve energy efficient bigdata processing and artificial intelligence in integrated device system-level. In this sense, uniform and reliable titanium oxide (TiOx) memristor array devices are fabricated to be utilized as constituent device element in hardware neural network, representing passive matrix array structure enabling vector-matrix multiplication process between multisignal and trained synaptic weight. In particular, in situ convolutional neural network hardware system is designed and implemented using a multiple 25 × 25 TiOx memristor arrays and the memristor device parameters are developed to bring global constant voltage programming scheme for entire cells in crossbar array without any voltage tuning peripheral circuit such as transistor. Moreover, the learning rate modulation during in situ hardware training process is successfully achieved due to superior TiOx memristor performance such as threshold uniformity (≈2.7%), device yield (> 99%), repetitive stability (≈3000 spikes), low asymmetry value of ≈1.43, ambient stability (6 months), and nonlinear pulse response. The learning rate modulable fast-converging in situ training based on direct memristor operation shows five times less training iterations and reduces training energy compared to the conventional hardware in situ training at ≈95.2% of classification accuracy.

Original languageEnglish
Article number2201117
JournalAdvanced Science
Volume9
Issue number22
DOIs
Publication statusPublished - 2022 Aug 5

Bibliographical note

Funding Information:
J.J. and S.G. contributed equally to this work. This work was supported by the KIST Institutional Program (2V09130‐21‐P036), a Korea University Grant, the National Research Foundation of Korea (NRF) funded by Ministry of Science and ICT (2022R1A2B5B02001455, 2020M3F3A2A03082825, 2022M3H4A1A01009526, and 2021R1A2C22013480), the Basic Science Research Program through the NRF funded by the Ministry of Education (2019R1A6A3A01095700 and 2020R1I1A1A01073059), and the EDA tool by the IC Design Education Center (IDEC).

Publisher Copyright:
© 2022 The Authors. Advanced Science published by Wiley-VCH GmbH.

Keywords

  • artificial synapses
  • hardware implementation
  • memristors
  • neuromorphic computing
  • uniformity

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • General Chemical Engineering
  • General Materials Science
  • Biochemistry, Genetics and Molecular Biology (miscellaneous)
  • General Engineering
  • General Physics and Astronomy

Fingerprint

Dive into the research topics of 'A Learning-Rate Modulable and Reliable TiOx Memristor Array for Robust, Fast, and Accurate Neuromorphic Computing'. Together they form a unique fingerprint.

Cite this