Mendeley出力
＜学術雑誌論文＞
RNN With a Recurrent Output Layer for Learning of Naturalness
| 作成者 | |
|---|---|
| 本文言語 | |
| 出版者 | |
| 発行日 | |
| 収録物名 | |
| 巻 | |
| 開始ページ | |
| 終了ページ | |
| 出版タイプ | |
| アクセス権 | |
| 関連DOI | |
| 関連DOI | |
| 関連URI | |
| 関連情報 | |
| 概要 | The behaviour of recurrent neural networks with a recurrent output layer (ROL) is described mathematically and it is shown that using ROL is not only advantageous, but is in fact crucial to obtaining ...satisfactory performance for the proposed naturalness learning. Conventional belief holds that employing ROL often substantially decreases the performance of a network or renders the network unstable, and ROL is consequently rarely used. The objective of this paper is to demonstrate that there are cases where it is necessary to use ROL. The concrete example shown models naturalness in handwritten letters.続きを見る |
| 目次 | 1 Introduction 2 Dynamics of RNN With a Recurrent Output Layer 3 RNN With a Recurrent Output Layer for Naturalness Learning 4 Experiments 5 Discussion 6 Conclusion |
本文ファイル
| ファイル | ファイルタイプ | サイズ | 閲覧回数 | 説明 |
|---|---|---|---|---|
iconip2007
|
585 KB | 626 |
詳細
| レコードID | |
|---|---|
| 査読有無 | |
| 主題 | |
| ISSN | |
| ISBN | |
| DOI | |
| 注記 | |
| 登録日 | 2017.06.08 |
| 更新日 | 2021.10.06 |