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 | 1145* | 2016 |

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 | 473 | 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 | 411 | 2013 |

Dropout as data augmentation X Bouthillier, K Konda, P Vincent, R Memisevic arXiv preprint arXiv:1506.08700, 2015 | 140* | 2015 |

Fast approximate natural gradient descent in a kronecker factored eigenbasis T George, C Laurent, X Bouthillier, N Ballas, P Vincent Advances in Neural Information Processing Systems 31, 2018 | 106 | 2018 |

Accounting for variance in machine learning benchmarks X Bouthillier, P Delaunay, M Bronzi, A Trofimov, B Nichyporuk, J Szeto, ... Proceedings of Machine Learning and Systems 3, 747-769, 2021 | 103 | 2021 |

Unreproducible research is reproducible X Bouthillier, C Laurent, P Vincent International Conference on Machine Learning, 725-734, 2019 | 90 | 2019 |

Efficient exact gradient update for training deep networks with very large sparse targets P Vincent, A De Brébisson, X Bouthillier Advances in Neural Information Processing Systems 28, 2015 | 62 | 2015 |

Survey of machine-learning experimental methods at NeurIPS2019 and ICLR2020 X Bouthillier, G Varoquaux Inria Saclay Ile de France, 2020 | 49 | 2020 |

Oríon-asynchronous distributed hyperparameter optimization X Bouthillier, C Tsirigotis, F Corneau-Tremblay, P Delaunay, ... October, 2019 | 13* | 2019 |

An evaluation of fisher approximations beyond kronecker factorization C Laurent, T George, X Bouthillier, N Ballas, P Vincent | 3 | 2018 |

Exact gradient updates in time independent of output size for the spherical loss family P Vincent, A de Brébisson, X Bouthillier arXiv preprint arXiv:1606.08061, 2016 | 3 | 2016 |

Accounting for variance and hyperparameter optimization in machine learning benchmarks X Bouthillier | | 2022 |

Improving Reproducibility of Benchmarks X Bouthillier | | |