output
20132025
most citedZoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

167 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing 2016Show all

6 papers · 1 filter

math.DS2016★ 49 cited

On the solutions of a second-order difference equations in terms of generalized Padovan sequences

Yacine Halim, Julius Fergy T. Rabago

This paper deals with the solution, stability character and asymptotic behavior of the rational difference equation \begin{equation*} x_{n+1}=\frac{αx_{n-1}+β}{ γx_{n}x_{n-1}},\qqu…

cs.CV2016★ 13 cited

Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark

Xu-Yao Zhang, Yoshua Bengio, Cheng-Lin Liu

Recent deep learning based methods have achieved the state-of-the-art performance for handwritten Chinese character recognition (HCCR) by learning discriminative representations di…

cs.CL2016★ 28 cited

First Result on Arabic Neural Machine Translation

Amjad Almahairi, Kyunghyun Cho, Nizar Habash +1

Neural machine translation has become a major alternative to widely used phrase-based statistical machine translation. We notice however that much of research on neural machine tra…

cs.LG2016★ 58 cited

On Multiplicative Integration with Recurrent Neural Networks

Yuhuai Wu, Saizheng Zhang, Ying Zhang +2

We introduce a general and simple structural design called Multiplicative Integration (MI) to improve recurrent neural networks (RNNs). MI changes the way in which information from…

cs.NE2016★ 167 cited

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

David Krueger, Tegan Maharaj, János Kramár +7

We propose zoneout, a novel method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain their previous values. Like dropout, zoneout…

cs.LG2016★ 55 cited

Recurrent Batch Normalization

Tim Cooijmans, Nicolas Ballas, César Laurent +2

We propose a reparameterization of LSTM that brings the benefits of batch normalization to recurrent neural networks. Whereas previous works only apply batch normalization to the i…