Sort by:

• Highly Influential Citations
• Citations
• Acceleration
• Velocity
• Recency

Learn More

Theano: A Python framework for fast computation of mathematical expressions

• Rami Al-Rfou', Guillaume Alain, +109 authors Ying Zhang
• ArXiv
• 2016

Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most… (More)

Convolutional Sequence to Sequence Learning

• Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann Dauphin
• ICML
• 2017

The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on… (More)

Language Modeling with Gated Convolutional Networks

• Yann Dauphin, Angela Fan, Michael Auli, David Grangier
• ICML
• 2017

The pre-dominant approach to language modeling to date is based on recurrent neural networks. Their success on this task is often linked to their ability to capture unbounded context. In this paper… (More)

Identifying and attacking the saddle point problem in high-dimensional non-convex optimization

• Yann Dauphin, Razvan Pascanu, Çaglar Gülçehre, Kyunghyun Cho, Surya Ganguli, Yoshua Bengio
• NIPS
• 2014

A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-Newton methods are… (More)

mixup: Beyond Empirical Risk Minimization

• Hongyi Zhang, Moustapha Cissé, Yann Dauphin, David Lopez-Paz
• ArXiv
• 2017

Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to… (More)

RMSProp and equilibrated adaptive learning rates for non-convex optimization

• Yann Dauphin, Harm de Vries, Junyoung Chung, Yoshua Bengio
• NIPS
• 2015

Parameter-specific adaptive learning rate methods are computationally efficient ways to reduce the ill-conditioning problems encountered when training large deep networks. Following recent work that… (More)

Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding

• Grégoire Mesnil, Yann Dauphin, +8 authors Geoffrey Zweig
• IEEE/ACM Transactions on Audio, Speech, and…
• 2015

Semantic slot filling is one of the most challenging problems in spoken language understanding (SLU). In this paper, we propose to use recurrent neural networks (RNNs) for this task, and present… (More)

Parseval Networks: Improving Robustness to Adversarial Examples

• Moustapha Cissé, Piotr Bojanowski, Edouard Grave, Yann Dauphin, Nicolas Usunier
• ICML
• 2017

We introduce Parseval networks, a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1. Parseval networks… (More)

Combining modality specific deep neural networks for emotion recognition in video

• Samira Ebrahimi Kahou, Christopher Joseph Pal, +24 authors Zhenzhou Wu
• ICMI
• 2013

In this paper we present the techniques used for the University of Montréal's team submissions to the 2013 Emotion Recognition in the Wild Challenge. The challenge is to classify the emotions… (More)

Better Mixing via Deep Representations

• Yoshua Bengio, Grégoire Mesnil, Yann Dauphin, Salah Rifai
• ICML
• 2013

It has previously been hypothesized, and supported with some experimental evidence, that deeper representations, when well trained, tend to do a better job at disentangling the underlying factors of… (More)

• ‹
• 1
• 2
• 3
• ›