Presentation 2021-12-02
Development of Spiking Neural Network with Mem Capacitor
Atsushi Sawada, Reon Oshio, Mutsumi Kimura, Renyuan Zhang, Yasuhiko Nakashima,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Research on artificial intelligence is developing rapidly, and there is an increasing need for the development of computers that specialize in the operation of artificial intelligence and enable low power consumption. One of these efforts is a neuromorphic system that mimics the neural circuits of the brain with hardware, and spiking neural networks in particular are attracting attention for their high energy efficiency. In this research, we propose a spiking neural network using a Mem capacitor and a pulse integrator circuit. By improving the conversion method between synaptic strength and capacitance on the circuit obtained by learning on simulation, we succeeded in reducing the loss of MNIST recognition accuracy to 9%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Memcapacitor / Spiking Neural Network / Pulse integrator circuit
Paper # VLD2021-32,ICD2021-42,DC2021-38,RECONF2021-40
Date of Issue 2021-11-24 (VLD, ICD, DC, RECONF)

Conference Information
Committee VLD / DC / RECONF / ICD / IPSJ-SLDM
Conference Date 2021/12/1(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Design Gaia 2021 -New Field of VLSI Design-
Chair Kazutoshi Kobayashi(Kyoto Inst. of Tech.) / Hiroshi Takahashi(Ehime Univ.) / Kentaro Sano(RIKEN) / Masafumi Takahashi(Kioxia) / Yuichi Nakamura(NEC)
Vice Chair Minako Ikeda(NTT) / Tatsuhiro Tsuchiya(Osaka Univ.) / Yoshiki Yamaguchi(Tsukuba Univ.) / Tomonori Izumi(Ritsumeikan Univ.) / Makoto Ikeda(Univ. of Tokyo)
Secretary Minako Ikeda(Osaka Univ.) / Tatsuhiro Tsuchiya(NEC) / Yoshiki Yamaguchi(Nihon Univ.) / Tomonori Izumi(Chiba Univ.) / Makoto Ikeda(NEC) / (Tokyo Inst. of Tech.)
Assistant / / Yukitaka Takemura(INTEL) / Yasunori Osana(Ryukyu Univ.) / Kosuke Miyaji(Shinshu Univ.) / Yoshiaki Yoshihara(キオクシア) / Takeshi Kuboki(Kyushu Univ.)

Paper Information
Registration To Technical Committee on VLSI Design Technologies / Technical Committee on Dependable Computing / Technical Committee on Reconfigurable Systems / Technical Committee on Integrated Circuits and Devices / Special Interest Group on System and LSI Design Methodology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Development of Spiking Neural Network with Mem Capacitor
Sub Title (in English) Reduction of recognition accuracy loss by improving the conversion method between synaptic strength and capacitance
Keyword(1) Memcapacitor
Keyword(2) Spiking Neural Network
Keyword(3) Pulse integrator circuit
1st Author's Name Atsushi Sawada
1st Author's Affiliation Nara Institute of Science and Technology(NAIST)
2nd Author's Name Reon Oshio
2nd Author's Affiliation Nara Institute of Science and Technology(NAIST)
3rd Author's Name Mutsumi Kimura
3rd Author's Affiliation Nara Institute of Science and Technology(NAIST)
4th Author's Name Renyuan Zhang
4th Author's Affiliation Nara Institute of Science and Technology(NAIST)
5th Author's Name Yasuhiko Nakashima
5th Author's Affiliation Nara Institute of Science and Technology(NAIST)
Date 2021-12-02
Paper # VLD2021-32,ICD2021-42,DC2021-38,RECONF2021-40
Volume (vol) vol.121
Number (no) VLD-277,ICD-278,DC-279,RECONF-280
Page pp.pp.87-92(VLD), pp.87-92(ICD), pp.87-92(DC), pp.87-92(RECONF),
#Pages 6
Date of Issue 2021-11-24 (VLD, ICD, DC, RECONF)