arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.00527cs.LGcs.NE
收藏

RNN中你不需要门

Gates Are Not What You Need in RNNs

Faculty of Computing, University of Latvia(拉脱维亚大学计算学院);Institute of Mathematics and Computer Science at University of Latvia(拉脱维亚大学数学与计算机科学研究所);Institute of Electronics and Computer Science(电子与计算机科学研究所)

Ronalds Zakovskis, Andis Draguns, Eliza Gaile, Emils Ozolins, Karlis Freivalds

AI总结:

提出无门控的残差循环单元RRU,基于残差连接、线性变换、ReLU和归一化,在多任务上超越传统门控RNN且对参数选择更具鲁棒性。

摘要:

循环神经网络在许多领域蓬勃发展。因此,我们可以看到新的RNN单元不断被开发出来,通常是通过以新的、原创的方式创建或使用门来实现的。但如果告诉你RNN中的门是冗余的呢?在本文中,我们提出了一种称为残差循环单元(RRU)的新循环单元,它超越了传统单元且不使用任何门。它基于残差快捷连接、线性变换、ReLU和归一化。为了评估我们单元的有效性,我们将其性能与广泛使用的GRU和LSTM单元以及最近提出的Mogrifier LSTM在多个任务上进行了比较,包括复调音乐建模、语言建模和情感分析。我们的实验表明,RRU在大多数任务上优于传统的门控单元。此外,它对参数选择具有更好的鲁棒性,允许在新任务中无需大量调优即可立即应用。我们已在TensorFlow中实现了RRU,代码可在https://github.com/LUMII-Syslab/RRU获取。

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑