| Presentation | 2017-11-09 Investigation of Hebbian-Like Learning Algorithm Based on Feedback Alignment for Autoencoder Takashi Matsubara, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Multilayer perceptrons have been trained by the back-propagation (BP) algorithm. Recent studies on feedback alignment (FA) have demonstrated that the BP does not necessarily require an accurate propagation of error signal in a layer-by-layer fashion, and attract attention as a bridge between the BP and a learning mechanism in biological neural networks. This study proposes an extension of FA for autoencoders and demonstrates that the proposed algorithm mimics the formation of Hebbian learning and can train an autoencoder. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | |
| Paper # | CCS2017-24 |
| Date of Issue | 2017-11-02 (CCS) |
| Conference Information | |
| Committee | CCS |
|---|---|
| Conference Date | 2017/11/9(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Osaka Univ. |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Naoki Wakamiya(Osaka Univ.) |
| Vice Chair | Mikio Hasegawa(Tokyo Univ. of Science) / Makoto Naruse(NICT) |
| Secretary | Mikio Hasegawa(Osaka Univ.) / Makoto Naruse(Tokyo City Univ.) |
| Assistant | Chisa Takano(Hirishima City Univ.) / Takashi Shimada(Univ. of Tokyo) / Tomoya Suzuki(Ibaraki Univ.) / Ryo Takahashi(AUT) |
| 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) | Investigation of Hebbian-Like Learning Algorithm Based on Feedback Alignment for Autoencoder |
| Sub Title (in English) | |
| Keyword(1) | |
| Keyword(2) | |
| 1st Author's Name | Takashi Matsubara |
| 1st Author's Affiliation | Kobe University(Kobe Univ.) |
| Date | 2017-11-09 |
| Paper # | CCS2017-24 |
| Volume (vol) | vol.117 |
| Number (no) | CCS-288 |
| Page | pp.pp.21-24(CCS), |
| #Pages | 4 |
| Date of Issue | 2017-11-02 (CCS) |