Eliza Gaile
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Eliza Gaile has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Andis Draguns
Institute of Mathematics and Computer Science University of Latvia Riga Latvia
3 shared publications - Karlis Freivalds
Institute of Electronics and Computer Science, 14 Dzerbenes Street, LV-1006 Riga, Latvia
3 shared publications - Emils Ozolins
Institute of Mathematics and Computer Science University of Latvia Riga Latvia
2 shared publications - Ronalds Zakovskis
Faculty of Computing University of Latvia Riga Latvia
2 shared publications Emīls Ozoliņš
Institute of Mathematics and Computer Science at University of Latvia
1 shared publication
Latest Publications
- Open Access
Gates Are Not What You Need in RNNs
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 .
Open AccessGates Are Not What You Need in RNNs
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 .