Depth-Gated Recurrent Neural Networks

By Kaisheng Yao, Trevor Cohn, Katerina Vylomova, Kevin Duh, Chris Dyer. 2015

79 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Quoc V. Le
2. Yoshua Bengio
3. Mohit Bansal
4. Zhe Gan
5. Sergey Levine
6. Ruslan Salakhutdinov
7. Kyunghyun Cho
8. Percy Liang

Citations in the corpus

• Adding Gradient Noise Improves Learning for Very Deep Networks (2015, background): “, 2015), and cell architectures (Cho et al., 2014a; Yao et al., 2015), these are not always sufficient or applicable in networks with complex structure over the latent variables.”
• Focused Hierarchical RNNs for Conditional Sequence Processing (2018, unknown): “Yao et al. (2015) uses a soft differential depth gate to connect the lower and the upper layers and Sordoni et al. (2015) explore a multi-scale architecture where the hierarchy is fixed.”