Precompensation, BIST and Analogue Berger Codes for Self-Healing of Neuromorphic RRAM

Tsung Chu Huang, Jeffae Schroff

研究成果: Conference contribution

摘要

Neuromorphic RRAM has become the most promising candidate for AI applications. But it suffers three issues including degradation, defects and errors. To overcome the three issues we proposed a precompensation technique for compensating resistive degradation. A linear-system-based BIST architecture is developed with proposed diagonal sliding march test can effectively and efficiently screen out the uncompensated degradation and permanent defects. Analog Berger codes is proposed for detecting transient errors for variation learning and self-checking for asymmetric errors. From evaluations, the precompensation takes only 5/B time for batch operations of B cycles. Proposed BIST approach and method can reduced 2LN march tests to 6N for L-level RRAMs. The self-healing ability is verified by analog-Berger-code error detection. From experiments using a typical neural network for MNIST handwritten digit dataset the network can be healed with only 2% of accuracy and about 35% of training steps.

原文English
主出版物標題Proceedings - 2018 IEEE 27th Asian Test Symposium, ATS 2018
發行者IEEE Computer Society
頁面173-178
頁數6
ISBN(電子)9781538694664
DOIs
出版狀態Published - 2018 十二月 6
事件27th IEEE Asian Test Symposium, ATS 2018 - Hefei, China
持續時間: 2018 十月 152018 十月 18

出版系列

名字Proceedings of the Asian Test Symposium
2018-October
ISSN(列印)1081-7735

Other

Other27th IEEE Asian Test Symposium, ATS 2018
國家China
城市Hefei
期間18-10-1518-10-18

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

指紋 深入研究「Precompensation, BIST and Analogue Berger Codes for Self-Healing of Neuromorphic RRAM」主題。共同形成了獨特的指紋。

引用此