Presentation 2016-03-22
An STDP control circuit and its evaluation using a Cu-MoOx-Al resistance change memory fabricated on a Si MOSFET
Kazumasa Tomizaki, Takashi Morie, Hideyuki Ando, Atsushi Fukuchi, Masashi Arita, Yasuo Takahashi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) With the progress of practical implementation of deep learning in neural networks, high-speed and low-power neural hardware (very-large-scale integrated circuits) that performs learning operation is being developed. The circuit architecture of such hardware is classified into digital and analog. Several digital neural integrated circuits have already been developed, and analog neural integrated circuits, which are expected to achieve higher performance, are also being developed. The most crucial issue for analog neural circuits is development of analog memory devices. Recently, as promising such devices, resistance change memory devices are actively studied, and some analog neural circuits with learning mechanisms using such devices have been reported. Spike-timing dependent plasticity (STDP) is often tried to implement as a learning rule. In this paper, we report evaluation results of analog memory characteristics of resistance change memory devices including Molybdenum oxide, design of memory control circuits implementing STDP, and experimental results of memory operation with asymmetric STDP characteristics.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) resistance change memory / neural network hardware / STDP control circuit / SET/RESET operation
Paper # NC2015-70
Date of Issue 2016-03-15 (NC)

Conference Information
Committee MBE / NC
Conference Date 2016/3/22(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Tamagawa University
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tetsuo Kobayashi(Kyoto Univ.) / Toshimichi Saito(Hosei Univ.)
Vice Chair Yutaka Fukuoka(Kogakuin Univ.) / Shigeo Sato(Tohoku Univ.)
Secretary Yutaka Fukuoka(akita noken) / Shigeo Sato(Kogakuin Univ.)
Assistant Takenori Oida(Kyoto Univ.) / Ryota Horie(Shibaura Inst. of Tech.) / Hiroyuki Kanbara(Tokyo Inst. of Tech.) / Hisanao Akima(Tohoku Univ.)

Paper Information
Registration To Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An STDP control circuit and its evaluation using a Cu-MoOx-Al resistance change memory fabricated on a Si MOSFET
Sub Title (in English)
Keyword(1) resistance change memory
Keyword(2) neural network hardware
Keyword(3) STDP control circuit
Keyword(4) SET/RESET operation
1st Author's Name Kazumasa Tomizaki
1st Author's Affiliation Kyushu Institute of Technology(Kyushu Inst. Tech.)
2nd Author's Name Takashi Morie
2nd Author's Affiliation Kyushu Institute of Technology(Kyushu Inst. Tech.)
3rd Author's Name Hideyuki Ando
3rd Author's Affiliation Kyushu Institute of Technology(Kyushu Inst. Tech.)
4th Author's Name Atsushi Fukuchi
4th Author's Affiliation Hokkaido University(Hokkaido Univ.)
5th Author's Name Masashi Arita
5th Author's Affiliation Hokkaido University(Hokkaido Univ.)
6th Author's Name Yasuo Takahashi
6th Author's Affiliation Hokkaido University(Hokkaido Univ.)
Date 2016-03-22
Paper # NC2015-70
Volume (vol) vol.115
Number (no) NC-514
Page pp.pp.7-12(NC),
#Pages 6
Date of Issue 2016-03-15 (NC)