Theano: a CPU and GPU math expression compiler J Bergstra, O Breuleux, F Bastien, P Lamblin, R Pascanu, G Desjardins, ... Proceedings of the Python for scientific computing conference (SciPy) 4 (3), 2010 | 1593 | 2010 |

Overcoming catastrophic forgetting in neural networks J Kirkpatrick, R Pascanu, N Rabinowitz, J Veness, G Desjardins, AA Rusu, ... Proceedings of the national academy of sciences 114 (13), 3521-3526, 2017 | 638 | 2017 |

Theano: A CPU and GPU math compiler in Python J Bergstra, O Breuleux, F Bastien, P Lamblin, R Pascanu, G Desjardins, ... Proc. 9th Python in Science Conf 1, 3-10, 2010 | 567 | 2010 |

Theano: A Python framework for fast computation of mathematical expressions R Al-Rfou, G Alain, A Almahairi, C Angermueller, D Bahdanau, N Ballas, ... arXiv preprint arXiv:1605.02688, 2016 | 416 | 2016 |

Progressive neural networks AA Rusu, NC Rabinowitz, G Desjardins, H Soyer, J Kirkpatrick, ... arXiv preprint arXiv:1606.04671, 2016 | 410 | 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 | 212 | 2013 |

Theano: Deep learning on gpus with python J Bergstra, F Bastien, O Breuleux, P Lamblin, R Pascanu, O Delalleau, ... NIPS 2011, BigLearning Workshop, Granada, Spain 3, 1-48, 2011 | 207 | 2011 |

Unsupervised and transfer learning challenge: a deep learning approach G Mesnil, Y Dauphin, X Glorot, S Rifai, Y Bengio, I Goodfellow, E Lavoie, ... Proceedings of the 2011 International Conference on Unsupervised and …, 2011 | 158 | 2011 |

Policy distillation AA Rusu, SG Colmenarejo, C Gulcehre, G Desjardins, J Kirkpatrick, ... arXiv preprint arXiv:1511.06295, 2015 | 157 | 2015 |

Understanding disentangling in -VAE CP Burgess, I Higgins, A Pal, L Matthey, N Watters, G Desjardins, ... arXiv preprint arXiv:1804.03599, 2018 | 111 | 2018 |

Natural neural networks G Desjardins, K Simonyan, R Pascanu Advances in Neural Information Processing Systems, 2071-2079, 2015 | 104 | 2015 |

Tempered Markov chain Monte Carlo for training of restricted Boltzmann machines G Desjardins, A Courville, Y Bengio, P Vincent, O Delalleau Proceedings of the thirteenth international conference on artificial …, 2010 | 102 | 2010 |

Theano: A Python framework for fast computation of mathematical expressions TTD Team, R Al-Rfou, G Alain, A Almahairi, C Angermueller, D Bahdanau, ... arXiv preprint arXiv:1605.02688, 2016 | 101 | 2016 |

Parallel tempering for training of restricted Boltzmann machines G Desjardins, A Courville, Y Bengio, P Vincent, O Delalleau Proceedings of the thirteenth international conference on artificial …, 2010 | 75 | 2010 |

Steerable Playlist Generation by Learning Song Similarity from Radio Station Playlists. F Maillet, D Eck, G Desjardins, P Lamere ISMIR, 345-350, 2009 | 69 | 2009 |

Empirical evaluation of convolutional RBMs for vision G Desjardins, Y Bengio DIRO, Université de Montréal, 1-13, 2008 | 57 | 2008 |

Disentangling factors of variation via generative entangling G Desjardins, A Courville, Y Bengio arXiv preprint arXiv:1210.5474, 2012 | 47 | 2012 |

Quadratic polynomials learn better image features J Bergstra, G Desjardins, P Lamblin, Y Bengio Technical report, 1337, 2009 | 41 | 2009 |

Adaptive parallel tempering for stochastic maximum likelihood learning of RBMs G Desjardins, A Courville, Y Bengio arXiv preprint arXiv:1012.3476, 2010 | 30 | 2010 |

Metric-free natural gradient for joint-training of boltzmann machines G Desjardins, R Pascanu, A Courville, Y Bengio arXiv preprint arXiv:1301.3545, 2013 | 22 | 2013 |