Theano: A Python framework for fast computation of mathematical expressions R Al-Rfou, G Alain, A Almahairi, C Angermueller, D Bahdanau, N Ballas, ... arXiv e-prints, arXiv: 1605.02688, 2016 | 1104* | 2016 |

Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription N Boulanger-Lewandowski, Y Bengio, P Vincent arXiv preprint arXiv:1206.6392, 2012 | 916 | 2012 |

Advances in optimizing recurrent networks Y Bengio, N Boulanger-Lewandowski, R Pascanu ICASSP, 2013 | 707 | 2013 |

Emonets: Multimodal deep learning approaches for emotion recognition in video SE Kahou, X Bouthillier, P Lamblin, C Gulcehre, V Michalski, K Konda, ... Journal on Multimodal User Interfaces 10, 99-111, 2016 | 493 | 2016 |

Combining modality specific deep neural networks for emotion recognition in video SE Kahou, C Pal, X Bouthillier, P Froumenty, Ç Gülçehre, R Memisevic, ... Proceedings of the 15th ACM on International conference on multimodal …, 2013 | 432 | 2013 |

Audio Chord Recognition with Recurrent Neural Networks N Boulanger-Lewandowski, Y Bengio, P Vincent ISMIR, 2013 | 260 | 2013 |

Deep learners benefit more from out-of-distribution examples Y Bengio, F Bastien, A Bergeron, N Boulanger-Lewandowski, T Breuel, ... JMLR W&CP: Proceedings of the Fourteenth International Conference on …, 2011 | 198 | 2011 |

Audio Chord Recognition with a Hybrid Recurrent Neural Network. S Sigtia, N Boulanger-Lewandowski, S Dixon ISMIR, 127-133, 2015 | 86 | 2015 |

High-dimensional sequence transduction N Boulanger-Lewandowski, Y Bengio, P Vincent 2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013 | 58 | 2013 |

A hybrid recurrent neural network for music transcription S Sigtia, E Benetos, N Boulanger-Lewandowski, T Weyde, ASA Garcez, ... 2015 IEEE international conference on acoustics, speech and signal …, 2015 | 57 | 2015 |

Theano: A Python framework for fast computation of mathematical expressions. arXiv R Al-Rfou, G Alain, A Almahairi, C Angermueller, D Bahdanau, N Ballas, ... arXiv preprint arXiv:1605.02688 10, 2016 | 52 | 2016 |

Discriminative non-negative matrix factorization for multiple pitch estimation N Boulanger-Lewandowski, Y Bengio, P Vincent ISMIR, 205--210, 2012 | 36 | 2012 |

Non-negative matrix factorization regularized by recurrent neural networks for audio processing NM Boulanger-Lewandowski, GJ Mysore, MD Hoffman US Patent 9,721,202, 2017 | 29 | 2017 |

Deep self-taught learning for handwritten character recognition Y Bengio, F Bastien, A Bergeron, N Boulanger-Lewandowski, ... NIPS* 2010 Deep Learning and Unsupervised Feature Learning Workshop, 2010 | 27* | 2010 |

Exploiting Long-Term Temporal Dependencies in NMF Using Recurrent Neural Networks with Application to Source Separation N Boulanger-Lewandowski, G Mysore, M Hoffman ICASSP, 2014 | 24 | 2014 |

Phone Sequence Modeling with Recurrent Neural Networks N Boulanger-Lewandowski, J Droppo, M Seltzer, D Yu ICASSP, 2014 | 18 | 2014 |

Intrusive STM imaging N Boulanger-Lewandowski, A Rochefort Physical Review B 83 (11), 115430, 2011 | 16 | 2011 |

Modeling high-dimensional audio sequences with recurrent neural networks N Boulanger-Lewandowski | 9 | 2014 |

EmoNets: Multimodal deep learning approaches for emotion recognition in video S Ebrahimi Kahou, X Bouthillier, P Lamblin, C Gulcehre, V Michalski, ... arXiv e-prints, arXiv: 1503.01800, 2015 | 1 | 2015 |

An Energy-Based Recurrent Neural Network for Multiple Fundamental Frequency Estimation N Boulanger-Lewandowski, P Vincent, Y Bengio Learning Workshop at Snowbird, 2011 | 1 | 2011 |