Presentation | 2018-03-13 A supervised learning rule of the pulsed neuron model for the arrival order recognition of the pulses Yuka Shimomura, Susumu Kuroyanagi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This research aims at extracting temporally large features in order to enable recognition of time series information. In order to realize it, we think that a stacked autoencoder can be applied to time series information processing by using a pulsed neuron model, and can compress spatial and temporal information simultaneously. Therefore, we propose a new supervised learning rule of pulsed neuron model for application to autoencoder. In the proposed learning rule, the connection weights and delays are simultaneously learned. Therefore, it enables clustering by the arrival order recognition of the pulses, and it enables extraction of effective temporal features. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Time series information processing / Neural network / Pulsed neuron model / Supervised learning rule |
Paper # | NC2017-73 |
Date of Issue | 2018-03-06 (NC) |
Conference Information | |
Committee | MBE / NC |
---|---|
Conference Date | 2018/3/13(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kikai-Shinko-Kaikan Bldg. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | ME, general |
Chair | Kazuki Nakajima(Univ. of Toyama) / Masafumi Hagiwara(Keio Univ.) |
Vice Chair | Masaki Kyoso(TCU) / Yutaka Hirata(Chubu Univ.) |
Secretary | Masaki Kyoso(Toyama Pref. Univ.) / Yutaka Hirata(Kindai Univ.) |
Assistant | Kim Juhyon(Univ. of Toyama) / Takumi Kobayashi(YNU) / Yoshihisa Shinozawa(Keio Univ.) / Keiichiro Inagaki(Chubu 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) | A supervised learning rule of the pulsed neuron model for the arrival order recognition of the pulses |
Sub Title (in English) | |
Keyword(1) | Time series information processing |
Keyword(2) | Neural network |
Keyword(3) | Pulsed neuron model |
Keyword(4) | Supervised learning rule |
1st Author's Name | Yuka Shimomura |
1st Author's Affiliation | Nagoya Institute of Technology(NIT) |
2nd Author's Name | Susumu Kuroyanagi |
2nd Author's Affiliation | Nagoya Institute of Technology(NIT) |
Date | 2018-03-13 |
Paper # | NC2017-73 |
Volume (vol) | vol.117 |
Number (no) | NC-508 |
Page | pp.pp.33-38(NC), |
#Pages | 6 |
Date of Issue | 2018-03-06 (NC) |