Title:
擬似リカレントニューラルネットワークに基づくエンコーダ‐デコーダモデル
Document Type and Number:
Japanese Patent JP2020501231
Kind Code:
A
Abstract:
開示される技術は、時間ステップにわたり並列に適用する畳み込み層と特徴次元にわたり並列に適用するミニマリスト再帰プーリング層とを交互にする擬似リカレントニューラルネットワーク（ＱＲＮＮ）を提供する。
Inventors:
Bradbury, James
Merry, steven, joseph
Option, Kaiming
Socher, richard
Merry, steven, joseph
Option, Kaiming
Socher, richard
Application Number:
JP2019523049A
Publication Date:
January 16, 2020
Filing Date:
November 03, 2017
Export Citation:
Assignee:
Sales Force dot com Incorporated
International Classes:
G06F40/44; G06F40/00; G06N3/04
Other References:
FANDONG MENG ET AL., ENCODING SOURCE LANGUAGE WITH CONVOLUTIONAL NETWORK FOR MACHINE TRANSLATION[ONLINE], JPN6020038163, 8 June 2015 (2015-06-08), pages 1 - 12, ISSN: 0004362255
RAMESH NALLAPATI ET AL., ABSTRACTIVE TEXT SUMMARIZATION USING SEQUENCE-TO-SEQUENCE RNNS AND BEYOND, JPN6020038166, 26 August 2016 (2016-08-26), pages 1 - 12, ISSN: 0004362256
ZHEN ZUO ET AL.: "Convolutional Recurrent Neural Networks: Learning Spatial Dependencies for Image Representation", PROCEEDINGS OF THE 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), JPN6020032715, 2015, pages 18 - 26, XP032795529, ISSN: 0004362257, DOI: 10.1109/CVPRW.2015.7301268
RAMESH NALLAPATI ET AL., ABSTRACTIVE TEXT SUMMARIZATION USING SEQUENCE-TO-SEQUENCE RNNS AND BEYOND, JPN6020038166, 26 August 2016 (2016-08-26), pages 1 - 12, ISSN: 0004362256
ZHEN ZUO ET AL.: "Convolutional Recurrent Neural Networks: Learning Spatial Dependencies for Image Representation", PROCEEDINGS OF THE 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), JPN6020032715, 2015, pages 18 - 26, XP032795529, ISSN: 0004362257, DOI: 10.1109/CVPRW.2015.7301268
Attorney, Agent or Firm:
Tadashige Ito
Tadahiko Ito
Shinsuke Onuki
Tadahiko Ito
Shinsuke Onuki