| Presentation | 2016-07-06 Feedforward supervised learning for deep neural networks with local competitiveness information Takashi Shinozaki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This study proposes a novel supervised learning method for deep neural networks that uses feedforward supervisory signal. The learning method requires sparse dynamics, and uses additional advance input as a supervisory signal to learn the target input. Before the target input, advance input, which produces the required classification label, is propagated through the entire network, and then the target input is processed with the after-effect of the advance input. We validated the efficiency of the proposed method by the visual recognition task of MNIST handwritten image dataset with a deep feedforward network. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep Neural Network / Deep Learning / Representation Learning / Self Organizing Map |
| Paper # | NC2016-15 |
| Date of Issue | 2016-06-28 (NC) |
| Conference Information | |
| Committee | NC / IPSJ-BIO / IBISML / IPSJ-MPS |
|---|---|
| Conference Date | 2016/7/4(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Okinawa Institute of Science and Technology |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Machine Learning Approach to Biodata Mining, and General |
| Chair | Shigeo Sato(Tohoku Univ.) / / Kenji Fukumizu(ISM) |
| Vice Chair | Masafumi Hagiwara(Keio Univ.) / / Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Kyoto Univ.) |
| Secretary | Masafumi Hagiwara(Kyoto Sangyo Univ.) / (Tokyo Inst. of Tech.) / Masashi Sugiyama / Hisashi Kashima(Univ. of Tokyo) / (Nagoya Inst. of Tech.) |
| Assistant | Hisanao Akima(Tohoku Univ.) / Yoshihisa Shinozawa(Keio Univ.) / / Toshihiro Kamishima(AIST) / Tomoharu Iwata(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Neurocomputing / Special Interest Group on Bioinformatics and Genomics / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Mathematical Modeling and Problem Solving |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Feedforward supervised learning for deep neural networks with local competitiveness information |
| Sub Title (in English) | |
| Keyword(1) | Deep Neural Network |
| Keyword(2) | Deep Learning |
| Keyword(3) | Representation Learning |
| Keyword(4) | Self Organizing Map |
| 1st Author's Name | Takashi Shinozaki |
| 1st Author's Affiliation | National Institute of Information and Communications Technology(NICT) |
| Date | 2016-07-06 |
| Paper # | NC2016-15 |
| Volume (vol) | vol.116 |
| Number (no) | NC-120 |
| Page | pp.pp.229-234(NC), |
| #Pages | 6 |
| Date of Issue | 2016-06-28 (NC) |