(Invited) 3D Neural Network: Monolithic Integration of Resistive-RAM Array with Oxide-Semiconductor FET. (8th September 2020)

• Record Type: Journal Article
• Authors: Kobayashi, Masaharu; Wu, Jixuan; Mo, Fei; Saraya, Takuya; Hiramoto, Toshiro
• Is Part Of: ECS transactions. Volume 98:Number 8(2020)
• Page Start: 57
• Page End: 61
• Publication Date: 2020-09-08
• Subjects: Electrochemistry -- Periodicals; Electrochemistry; Periodicals; Electronic journals; Electronic journal; 541.37
• DOI: 10.1149/09808.0057ecst
• Languages: English
• ISSNs: 1938-5862

Abstract

Abstract : We have developed monolithic integration of RRAM array and oxide semiconductor channel access transistor in 3D stack, achieved uniform memory characteristics of 1T1R cells at each layer, and demonstrated basic functionality of XNOR operation as in-memory computing for binary neural network AI applications. The impact of RRAM bit error rate on neural network is also investigated. 3D neural network built by this architecture enables area-efficient, low-power and low-latency computing in machine learning accelerator.