Presentation 2021-03-03
A Study on Feature Extraction of signal arrival order using unsupervised learning of the pulsed neuron model
Kaya Teramoto, Susumu Kuroyanagi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) For time series information processing using pulsed neuron models, a supervised learning rule is proposed that enables clustering based on the ordinal relation of input pulses by simultaneously learning of the connection weights and delays of the pulse neuron model. However, clustering by supervised learning rule does not extract features inherent in the data. In this paper, We apply this learning rule to unsupervised learning to verify whether it is possible to perform clustering that captures the temporal characteristics of the arrival order relation of pulses.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural network / Pulsed neuron model / Time series information processing / Unsupervised learning
Paper # NC2020-51
Date of Issue 2021-02-24 (NC)

Conference Information
Committee NC / MBE
Conference Date 2021/3/3(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Neuro Computing, Medical Engineering, etc.
Chair Kazuyuki Samejima(Tamagawa Univ) / Takashi Watanabe(Tohoku Univ.)
Vice Chair Rieko Osu(Waseda Univ.) / Ryuhei Okuno(Setsunan Univ.)
Secretary Rieko Osu(NTT) / Ryuhei Okuno(ATR)
Assistant Ken Takiyama(TUAT) / Nobuhiko Wagatsuma(Toho Univ.) / Akihiro Karashima(Tohoku Inst. of Tech.) / Jun Akazawa(Meiji Univ. of Integrative Medicine)

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) A Study on Feature Extraction of signal arrival order using unsupervised learning of the pulsed neuron model
Sub Title (in English)
Keyword(1) Neural network
Keyword(2) Pulsed neuron model
Keyword(3) Time series information processing
Keyword(4) Unsupervised learning
1st Author's Name Kaya Teramoto
1st Author's Affiliation Nagoya Institute of Technology University(NIT)
2nd Author's Name Susumu Kuroyanagi
2nd Author's Affiliation Nagoya Institute of Technology University(NIT)
Date 2021-03-03
Paper # NC2020-51
Volume (vol) vol.120
Number (no) NC-403
Page pp.pp.47-52(NC),
#Pages 6
Date of Issue 2021-02-24 (NC)