A novel design for a gated recurrent network with attentional memories

Libin Sun, Gao Biao, Haobin Shi

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Recurrent neural networks (RNN) are used for pro-cessing the temporal dynamics of complex sequential information. Existing recurrent neural networks, such as Long Short-Term Memory (LSTM) and its variant, Gated Recurrent Unit (GRU), are used to control current and historical information. This study proposes a novel design for a gated recurrent neural network with an attention mechanism, named the Attentional Memory Unit (AMU), which gives the recurrent neural network an attention capability. This design uses a gated mechanism and a generalized attention mechanism so that it can be adaptively adjusted in the spatial and temporal sense to allow the application of the attention mechanism for different scenarios. The experimental results verify that the proposed AMU significantly boosts the power of RNNs.

源语言英语
主期刊名Proceedings - 2022 International Conference on Computer Engineering and Artificial Intelligence, ICCEAI 2022
编辑Pan Lin, Yong Yang
出版商Institute of Electrical and Electronics Engineers Inc.
522-527
页数6
ISBN(电子版)9781665468039
DOI
出版状态已出版 - 2022
活动2022 International Conference on Computer Engineering and Artificial Intelligence, ICCEAI 2022 - Shijiazhuang, 中国
期限: 22 7月 202224 7月 2022

出版系列

姓名Proceedings - 2022 International Conference on Computer Engineering and Artificial Intelligence, ICCEAI 2022

会议

会议2022 International Conference on Computer Engineering and Artificial Intelligence, ICCEAI 2022
国家/地区中国
Shijiazhuang
时期22/07/2224/07/22

指纹

探究 'A novel design for a gated recurrent network with attentional memories' 的科研主题。它们共同构成独一无二的指纹。

引用此