Presentation 2019-12-06
Neural Networks for Constructing Logical Operations
Yuma Saito, Masafumi Hagiwara,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this research, we aim to integrate both conventional statistical processing and exact logic processing into the same framework of neural networks. As the first step to this goal, we propose the novel neural networks which can learn how to perform logical operations by gradient descent method. Our proposed networks consist of modules that perform a basic logical operations such as AND, OR, NOT, and the connections between them are learned as binarized value 0, 1. In our experiments, we confirmed that our proposed models could construct simple logical operations such as 2-variable XOR automatically.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural networks / Gradient descent method / Logical operations
Paper # MBE2019-57,NC2019-48
Date of Issue 2019-11-29 (MBE, NC)

Conference Information
Committee NC / MBE
Conference Date 2019/12/6(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Toyohashi Tech
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Hayaru Shouno(UEC) / Taishin Nomura(Osaka Univ.)
Vice Chair Kazuyuki Samejima(Tamagawa Univ) / Takashi Watanabe(Tohoku Univ.)
Secretary Kazuyuki Samejima(NAIST) / Takashi Watanabe(NTT)
Assistant Takashi Shinozaki(NICT) / Ken Takiyama(TUAT) / Yasuyuki Suzuki(Osaka Univ.) / Akihiro Karashima(Tohoku Inst. of Tech.)

Paper Information
Registration To Technical Committee on Neurocomputing / Technical Committee on ME and Bio Cybernetics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Neural Networks for Constructing Logical Operations
Sub Title (in English)
Keyword(1) Neural networks
Keyword(2) Gradient descent method
Keyword(3) Logical operations
1st Author's Name Yuma Saito
1st Author's Affiliation Keio University(Keio Univ.)
2nd Author's Name Masafumi Hagiwara
2nd Author's Affiliation Keio University(Keio Univ.)
Date 2019-12-06
Paper # MBE2019-57,NC2019-48
Volume (vol) vol.119
Number (no) MBE-327,NC-328
Page pp.pp.73-78(MBE), pp.73-78(NC),
#Pages 6
Date of Issue 2019-11-29 (MBE, NC)