Metal-oxide Based, CMOS-compatible ECRAM for Deep Learning Accelerator
2019 IEEE International Electron Devices Meeting (IEDM)（2019）
Key words
deep learning accelerator,CMOS-compatible metal-oxide based electrochemical random-access memory,metal-oxide based CMOS-compatible ECRAM,high-speed low-power neuromorphic computing,linear conductance update,symmetric conductance update,high temperature treatments,resistive switching,BEOL compatibility,voltage pulse amplitude,fully-parallel array operations,stochastic update scheme,zero-shifting technique,stochastic gradient descent algorithm,MO-ECRAM array,time 10.0 ns
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined