TY - GEN
T1 - Development of Non-Volatile Tunnel-FET Memory as a Synaptic Device for Low-Power Spiking Neural Networks
AU - Kino, Hisashi
AU - Fukushima, Takafumi
AU - Tanaka, Tetsu
N1 - Funding Information:
ACKNOWLEDGMENTS This work was supported by the Frontier Research Institute for Interdisciplinary Sciences (FRIS) Tohoku University. The work is also supported by the VLSI Design and Education Center (VDEC), the University of Tokyo, in collaboration with Cadence Design Systems. This work was performed in the Micro/Nano-Machining Research and Education Center at Tohoku University.
Funding Information:
This work was supported by the Frontier Research Institute for Interdisciplinary Sciences (FRIS) Tohoku University. The work is also supported by the VLSI Design and Education Center (VDEC), the University of Tokyo, in collaboration with Cadence Design Systems. This work was performed in the Micro/Nano-Machining Research and Education Center at Tohoku University.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/4
Y1 - 2020/4
N2 - Spiking neural network (SNN) has attracted much attention as next-generation neural networks. To realize SNN, the spike-timing-dependent plasticity (STDP) is one of the critical characteristics. In this study, we demonstrated the STDP of a biological synapse with non-volatile tunnel-field-effect transistor (FET) memory. Tunnel FET is a promising candidate to reduce the power consumption owing to the steep subthreshold characteristics. Therefore, non-volatile tunnel-FET memory we proposed has the possibility to realize low-power SNN. This paper reported the current-voltage characteristics, the memory window., and the STDP characteristics of the nonvolatile tunnel-FET memory.
AB - Spiking neural network (SNN) has attracted much attention as next-generation neural networks. To realize SNN, the spike-timing-dependent plasticity (STDP) is one of the critical characteristics. In this study, we demonstrated the STDP of a biological synapse with non-volatile tunnel-field-effect transistor (FET) memory. Tunnel FET is a promising candidate to reduce the power consumption owing to the steep subthreshold characteristics. Therefore, non-volatile tunnel-FET memory we proposed has the possibility to realize low-power SNN. This paper reported the current-voltage characteristics, the memory window., and the STDP characteristics of the nonvolatile tunnel-FET memory.
KW - MONOS
KW - SNN
KW - STDP
KW - Tunnel FET
UR - http://www.scopus.com/inward/record.url?scp=85091978524&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85091978524&partnerID=8YFLogxK
U2 - 10.1109/EDTM47692.2020.9118027
DO - 10.1109/EDTM47692.2020.9118027
M3 - Conference contribution
AN - SCOPUS:85091978524
T3 - 4th Electron Devices Technology and Manufacturing Conference, EDTM 2020 - Proceedings
BT - 4th Electron Devices Technology and Manufacturing Conference, EDTM 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th Electron Devices Technology and Manufacturing Conference, EDTM 2020
Y2 - 6 April 2020 through 21 April 2020
ER -