Presentation 2016-11-04
Unsupervised Learning with Spike-Timing Dependent Delay Learning Model
Takashi Matsubara,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Precious timing of neuronal spikes is considered to play an important role in signal transmission and processing in central nervous systems, and mimicking such system contributes to development of an efficient information processing chip requiring less energy and circuit area. Adaptation of spike timing is also known as delay learning. However, it still remains unclear how biological nervous system adjusts spike timing or what learning algorithm achieves a desired network structure. This paper presents an unsupervised learning algorithm, which considers a simple spiking neural network as a probabilistic model and trains it according to EM algorithm. Learning procedure shown in the presented algorithm is similar to those shown in previous physiological studies and a plausible model of biological delay learning.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Spiking Neural Network / Delay Learning / Unsupervised Learning / EM algorithm
Paper # CCS2016-32
Date of Issue 2016-10-28 (CCS)

Conference Information
Committee CCS
Conference Date 2016/11/4(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kyoto Sangyo Univ. (Musubiwaza Bldg.)
Topics (in Japanese) (See Japanese page)
Topics (in English) Interaction and Communication, etc.
Chair Yasuhiro Tsubo(Ritsumeikan Univ.)
Vice Chair Naoki Wakamiya(Osaka Univ.) / Mikio Hasegawa(Tokyo Univ. of Science)
Secretary Naoki Wakamiya(Kyoto Sangyo Univ.) / Mikio Hasegawa(Osaka Univ.)
Assistant Takayuki Kimura(Nippon Inst. of Tech.) / Song-Ju Kim(NIMS) / Ryo Takahashi(Kyoto Univ.) / Hidehiro Nakano(Tokyo City Univ.)

Paper Information
Registration To Technical Committee on Complex Communication Sciences
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Unsupervised Learning with Spike-Timing Dependent Delay Learning Model
Sub Title (in English)
Keyword(1) Spiking Neural Network
Keyword(2) Delay Learning
Keyword(3) Unsupervised Learning
Keyword(4) EM algorithm
1st Author's Name Takashi Matsubara
1st Author's Affiliation Kobe University(Kobe Univ.)
Date 2016-11-04
Paper # CCS2016-32
Volume (vol) vol.116
Number (no) CCS-285
Page pp.pp.13-16(CCS),
#Pages 4
Date of Issue 2016-10-28 (CCS)