Title :
3D synaptic architecture with ultralow sub-10 fJ energy per spike for neuromorphic computation
Author :
I-Ting Wang ; Yen-Chuan Lin ; Yu-Fen Wang ; Chung-Wei Hsu ; Tuo-Hung Hou
Author_Institution :
Dept. of Electron. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Abstract :
A high-density 3D synaptic architecture based on self-rectifying Ta/TaOx/TiO2/Ti RRAM is proposed as an energy- and cost-efficient neuromorphic computation hardware. The device shows excellent analog synaptic features that can be accurately described by the physical and compact models. Ultra-low energy consumption comparable to that of a biological synapse (<;10 fJ/spike) has been demonstrated for the first time.
Keywords :
low-power electronics; resistive RAM; tantalum; tantalum compounds; titanium; titanium compounds; Ta-TaOx-TiO2-Ti; analog synaptic features; biological synapse; compact models; high-density 3D synaptic architecture; neuromorphic computation hardware; physical models; self-rectifying RRAM; ultralow energy consumption; Biology; Computer architecture; Equations; Mathematical model; Neuromorphics; Three-dimensional displays; Training;
Conference_Titel :
Electron Devices Meeting (IEDM), 2014 IEEE International
DOI :
10.1109/IEDM.2014.7047127
