Presentation | 2016-09-05 The Validity of Network In Network as a Visual System Satoshi Suzuki, Hayaru Shouno, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In recent years, Deep Convolutional Neural Network (DCNN) has shown excellent performance in image recognition field. DCNN is one of the multi-layer neural networks, which can automatically obtain feature representation from data. Neocognitron is the prototype of DCNN, which was proposed by Fukushima in early 80's. It is inspired by the hierarchical structure in the 18 field of cat brain which corresponds to the initial visual cortex.On the other hand, Network In Network (NIN) method was proposed by Lin et al.. NIN technology has shown state-of-the-art performance in many image recognition task. However, discussion of the physiological relationship of NIN and DCNN which is brain inspired model was insufficient. In this work, we make the filters that are created by NIN, and show that these filters have the same function as the orientation selectivity in the early visual cortex. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Deep Convolutional Neural Network / Network In Network / Orientation Selectivity Map |
Paper # | PRMU2016-68,IBISML2016-23 |
Date of Issue | 2016-08-29 (PRMU, IBISML) |
Conference Information | |
Committee | PRMU / IPSJ-CVIM / IBISML |
---|---|
Conference Date | 2016/9/5(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Eisaku Maeda(NTT) / / Kenji Fukumizu(ISM) |
Vice Chair | Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / / Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Kyoto Univ.) |
Secretary | Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / / Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Nagoya Inst. of Tech.) |
Assistant | Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / / Toshihiro Kamishima(AIST) / Tomoharu Iwata(NTT) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media / Technical Committee on Infomation-Based Induction Sciences and Machine Learning |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | The Validity of Network In Network as a Visual System |
Sub Title (in English) | From the Point of View of the Orientation Selectivity Map |
Keyword(1) | Deep Convolutional Neural Network |
Keyword(2) | Network In Network |
Keyword(3) | Orientation Selectivity Map |
1st Author's Name | Satoshi Suzuki |
1st Author's Affiliation | The University of Electro-Communications(UEC) |
2nd Author's Name | Hayaru Shouno |
2nd Author's Affiliation | The University of Electro-Communications(UEC) |
Date | 2016-09-05 |
Paper # | PRMU2016-68,IBISML2016-23 |
Volume (vol) | vol.116 |
Number (no) | PRMU-208,IBISML-209 |
Page | pp.pp.113-120(PRMU), pp.113-120(IBISML), |
#Pages | 8 |
Date of Issue | 2016-08-29 (PRMU, IBISML) |