Yoshua Bengio

Residual Connections Encourage Iterative Inference

Stanisław Jastrzębski, Devansh Arpit, Nicolas Ballas, Vikas Verma, Tong Che, Yoshua Bengio

Comments First two authors contributed equally. Published in ICLR 2018

Learning to Compute Word Embeddings On the Fly

Dzmitry Bahdanau, Tom Bosc, Stanisław Jastrzębski, Edward Grefenstette, Pascal Vincent, Yoshua Bengio

Disentangling the independently controllable factors of variation by interacting with the world

Valentin Thomas, Emmanuel Bengio, William Fedus, Jules Pondard, Philippe Beaudoin, Hugo Larochelle, Joelle Pineau, Doina Precup, Yoshua Bengio

Comments Presented at NIPS 2017 Learning Disentangling Representations Workshop

Learning Anonymized Representations with Adversarial Neural Networks

Clément Feutry, Pablo Piantanida, Yoshua Bengio, Pierre Duhamel

Comments 20 pages, 6 figures

Twin Networks: Matching the Future for Sequence Generation

Dmitriy Serdyuk, Nan Rosemary Ke, Alessandro Sordoni, Adam Trischler, Chris Pal, Yoshua Bengio

Comments 12 pages, 3 figures, published at ICLR 2018

Deep Complex Networks

Chiheb Trabelsi, Olexa Bilaniuk, Ying Zhang, Dmitriy Serdyuk, Sandeep Subramanian, João Felipe Santos, Soroush Mehri, Negar Rostamzadeh, Yoshua Bengio, Christopher J Pal

Towards end-to-end spoken language understanding

Dmitriy Serdyuk, Yongqiang Wang, Christian Fuegen, Anuj Kumar, Baiyang Liu, Yoshua Bengio

Comments submitted to ICASSP 2018

FigureQA: An Annotated Figure Dataset for Visual Reasoning

Samira Ebrahimi Kahou, Vincent Michalski, Adam Atkinson, Akos Kadar, Adam Trischler, Yoshua Bengio

Comments workshop paper at ICLR 2018

ChatPainter: Improving Text to Image Generation using Dialogue

Shikhar Sharma, Dendi Suhubdy, Vincent Michalski, Samira Ebrahimi Kahou, Yoshua Bengio

Boundary-Seeking Generative Adversarial Networks

R Devon Hjelm, Athul Paul Jacob, Tong Che, Adam Trischler, Kyunghyun Cho, Yoshua Bengio

Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask

Stylianos Ioannis Mimilakis, Konstantinos Drossos, João F. Santos, Gerald Schuller, Tuomas Virtanen, Yoshua Bengio

Graph Attention Networks

Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio

Comments To appear at ICLR 2018. 12 pages, 2 figures

MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation

Konstantinos Drossos, Stylianos Ioannis Mimilakis, Dmitriy Serdyuk, Gerald Schuller, Tuomas Virtanen, Yoshua Bengio

A Deep Reinforcement Learning Chatbot (Short Version)

Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeswar, Alexandre de Brebisson, Jose M. R. Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau, Yoshua Bengio

Comments 9 pages, 1 figure, 2 tables; presented at NIPS 2017, Conversational AI: "Today's Practice and Tomorrow's Potential" Workshop

Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses

Ryan Lowe, Michael Noseworthy, Iulian V. Serban, Nicolas Angelard-Gontier, Yoshua Bengio, Joelle Pineau

Comments ACL 2017

Journal ref Proceedings of the 55th annual meeting on Association for Computational Linguistics (2017), pp. 1116-1126

A3T: Adversarially Augmented Adversarial Training

Akram Erraqabi, Aristide Baratin, Yoshua Bengio, Simon Lacoste-Julien

Comments accepted for an oral presentation in Machine Deception Workshop, NIPS 2017

Efficient EM Training of Gaussian Mixtures with Missing Data

Olivier Delalleau, Aaron Courville, Yoshua Bengio

ObamaNet: Photo-realistic lip-sync from text

Rithesh Kumar, Jose Sotelo, Kundan Kumar, Alexandre de Brebisson, Yoshua Bengio

Dendritic error backpropagation in deep cortical microcircuits

João Sacramento, Rui Ponte Costa, Yoshua Bengio, Walter Senn

Comments 27 pages, 5 figures, 10 pages supplementary information

GibbsNet: Iterative Adversarial Inference for Deep Graphical Models

Alex Lamb, Devon Hjelm, Yaroslav Ganin, Joseph Paul Cohen, Aaron Courville, Yoshua Bengio

Comments NIPS 2017

Measuring the tendency of CNNs to Learn Surface Statistical Regularities

Jason Jo, Yoshua Bengio

Comments Submitted

Plan, Attend, Generate: Planning for Sequence-to-Sequence Models

Francis Dutil, Caglar Gulcehre, Adam Trischler, Yoshua Bengio

Comments NIPS 2017

Z-Forcing: Training Stochastic Recurrent Networks

Anirudh Goyal, Alessandro Sordoni, Marc-Alexandre Côté, Nan Rosemary Ke, Yoshua Bengio

Comments To appear in NIPS'17

Variational Bi-LSTMs

Samira Shabanian, Devansh Arpit, Adam Trischler, Yoshua Bengio

ACtuAL: Actor-Critic Under Adversarial Learning

Anirudh Goyal, Nan Rosemary Ke, Alex Lamb, R Devon Hjelm, Chris Pal, Joelle Pineau, Yoshua Bengio

Sharp Minima Can Generalize For Deep Nets

Laurent Dinh, Razvan Pascanu, Samy Bengio, Yoshua Bengio

Comments 8.5 pages of main content, 2.5 of bibliography and 1 page of appendix

Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks

Nan Rosemary Ke, Anirudh Goyal, Olexa Bilaniuk, Jonathan Binas, Laurent Charlin, Chris Pal, Yoshua Bengio

Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net

Anirudh Goyal, Nan Rosemary Ke, Surya Ganguli, Yoshua Bengio

Comments To appear at NIPS 2017

A Deep Reinforcement Learning Chatbot

Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeshwar, Alexandre de Brebisson, Jose M. R. Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau, Yoshua Bengio

Comments 40 pages, 9 figures, 11 tables

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio