English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recurrent neural networks have flourished in many areas. Consequently, we cansee new RNN cells being developed continuously, usually by creating or usinggates in a new, original way. But what if we told you that gates in RNNs areredundant? In this paper, we propose a new recurrent cell called ResidualRecurrent Unit (RRU) which beats traditional cells and does not employ a singlegate. It is based on the residual shortcut connection, linear transformations,ReLU, and normalization. To evaluate our cell's effectiveness, we compare itsperformance against the widely-used GRU and LSTM cells and the recentlyproposed Mogrifier LSTM on several tasks including, polyphonic music modeling,language modeling, and sentiment analysis. Our experiments show that RRUoutperforms the traditional gated units on most of these tasks. Also, it hasbetter robustness to parameter selection, allowing immediate application in newtasks without much tuning. We have implemented the RRU in TensorFlow, and thecode is made available at https://github.com/LUMII-Syslab/RRU .

Gates Are Not What You Need in RNNs