Hugo Larochelle is a Research Scientist at Google Brain and lead of the Montreal Google Brain team. Conclusion• Deep Learning : powerful arguments & generalization priciples• Unsupervised Feature Learning is crucial many new algorithms and applications in recent years• Deep Learning suited for multi-task learning, domain adaptation and semi-learning with few labels Massimo Caccia, Lucas Caccia, William Fedus, sistemas e métodos para realizar otimização bayesiana, Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program), On-the-Fly Adaptation of Source Code Models using Meta-Learning, Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling. Solving them without Task Supervision at Test-Time. He is also a member of Yoshua Bengio's Mila and an Adjunct Professor at the Université de Montréal. Ruslan Salakhutdinov, Hugo Larochelle ; JMLR W&CP 9:693-700, 2010. All over the world, great advances in the field of AI are the direct result of the Universite de Montreal professor and Mila director, said Larochelle. For more information, see our Privacy Statement. William Fedus, Prajit Ramachandran, Rishabh Agarwal, Small-GAN: Speeding up GAN Training using Core-Sets. }, classes I have taught at Université de Sherbrooke, [LATEST on arXiv preprint arXiv:2007.06700 (2020-07-13)], [Also on arXiv preprint arXiv:1910.13540 (2019-10-29)], [Also on arXiv preprint arXiv:1903.03096 (2019-03-07)], [Also on arXiv preprint arXiv:1811.02549 (2018-11-06)], [Also on arXiv preprint arXiv:1903.07714 (2019-03-18)]. Learn more. Welcome to the show, Hugo. Tong Che, Ruixiang Zhang, Jascha Sohl-Dickstein. Anirudh Goyal Alias Parth Goyal, Philemon Brakel, William Fedus, Soumye Singhal, Timothy Lillicrap, Sergey Levine, Laurent Dinh, Jascha Sohl-Dickstein, Razvan Pascanu and. Hyperbolic Discounting and Learning over Multiple Horizons. Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin. Authored publications Google publications Other publications. We use optional third-party analytics cookies to understand how you use GitHub.com so we can build better products. Learn more. Contact All American Speakers Bureau to inquire about speaking fees and availability, and book the best keynote speaker for your next live or virtual event. Machine Intelligence. Even myself when I was teaching, I was putting a lot of material on YouTube to allow for people to learn. Previously, he was an Associate Professor at the University of Sherbrooke. Hugo Larochelle - Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead . The Google Brain Team joined 300 other researchers, professionals and students to talk about the developments in … Neural networks [9.1] : Computer vision - motivation - YouTube A Universal Representation Transformer Layer for Few-Shot Image Classification. Simon Brodeur, Ethan Perez, Ankesh Anand, Florian Golemo, Luca Celotti, Florian Strub, Jean Rouat, Hugo Larochelle and Aaron C. Courville ICLR 2018 (2018-01-01) Larochelle offers an online deep learning and neural network course which is free and accessible on Youtube. Learning Graph Structure With A Finite-State Automaton Layer. Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal, The Hanabi Challenge: A New Frontier for AI Research, On Catastrophic Interference in Atari 2600 Games. Hugo Larochelle course - http://info.usherbrooke.ca/hlarochelle/neural_networks/content.html - deeplearning.sh William Fedus, Dibya Ghosh, John D. Martin, Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction, Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks, Learning Graph Structure With A Finite-State Automaton Layer, Acquiring and Predicting Multidimensional Diffusion (MUDI) Data: An Open Challenge. Hugo Larochelle: Hi. TechAide AI4Good 2020 - Olivier Corradi: Estimation of marginal emissions in … Hugo Larochelle Hugo’s work concentrates on machine learning -the development of algorithms capable of extracting concepts and abstractions from data. Neural networks [9.8] : Computer vision - example - YouTube My research focuses on the study and development of deep learning algorithms. Hugo Larochelle is a Research Scientist at Google Brain and lead of the Montreal Google Brain team. Held virtually for the first time, this conference includes invited talks, demonstrations and presentations of some of the latest in machine learning research. Previously, he was an Associate Professor at the University of Sherbrooke. Mohammad Havaei 1 , Axel Davy 2 , David Warde-Farley 3 , Antoine Biard 4 , Aaron Courville 3 , Yoshua Bengio 3 , Chris Pal 5 , Pierre-Marc Jodoin 6 , Hugo Larochelle 6 Affiliations 1 Université de Sherbrooke, Sherbrooke, Qc, Canada. Machine Learning Practitioners have different personalities. Are Few-shot Learning Benchmarks Too Simple ? Learn more, We use analytics cookies to understand how you use our websites so we can make them better, e.g. We use essential cookies to perform essential website functions, e.g. string(2) "en" We use optional third-party analytics cookies to understand how you use GitHub.com so we can build better products. Biography and booking information for Hugo Larochelle, Research Scientist at Google. This week marks the beginning of the 34 th annual Conference on Neural Information Processing Systems (NeurIPS 2020), the biggest machine learning conference of the year. Valentin Thomas, Emmanuel Bengio, William Fedus, Jules Pondard, Philippe Beaudoin. Hugo Larochelle. Since 2012, he has been cited 7,686 times in the Google Scholar index. Uniform Priors for Data-Efficient Transfer. About. http://info.usherbrooke.ca/hlarochelle/neural_networks/content.html, curl -O ftp://tlp.limsi.fr/public/emnlp05.pdf, curl -O http://aaroncourville.wordpress.com/, curl -O http://acl.ldc.upenn.edu/W/W02/W02-1001.pdf, curl -O http://aclweb.org/anthology-new/N/N12/N12-1005.pdf, curl -O http://ai.stanford.edu/~ehhuang/, curl -O http://ai.stanford.edu/~koller/, curl -O http://ai.stanford.edu/~quocle/, curl -O http://ai.stanford.edu/~quocle/LeKarpenkoNgiamNg.pdf, curl -O http://ai.stanford.edu/~rajatr/, curl -O http://ai.stanford.edu/~rajatr/papers/expsc_ijcai09.pdf, curl -O http://arxiv.org/pdf/1010.3467.pdf, curl -O http://arxiv.org/pdf/1011.4088v1.pdf, curl -O http://arxiv.org/pdf/1107.1805v1.pdf, curl -O http://arxiv.org/pdf/1206.5533v1.pdf, curl -O http://arxiv.org/pdf/1206.6407.pdf, curl -O http://arxiv.org/pdf/1207.0580.pdf, curl -O http://arxiv.org/pdf/1302.4389v4.pdf, curl -O http://bengio.abracadoudou.com/, curl -O http://books.nips.cc/papers/files/nips22/NIPS2009_0817.pdf, curl -O http://books.nips.cc/papers/files/nips22/NIPS2009_0933.pdf, curl -O http://brainlogging.wordpress.com/, curl -O http://cilvr.cs.nyu.edu/diglib/lsml/bottou-sgd-tricks-2012.pdf, curl -O http://cs.nyu.edu/~fergus/pmwiki/pmwiki.php, curl -O http://cs.nyu.edu/~koray/publis/jarrett-iccv-09.pdf, curl -O http://cs.nyu.edu/~wanli/dropc/dropc.pdf, curl -O http://cs.stanford.edu/~jngiam/, curl -O http://cs.stanford.edu/~jngiam/papers/NgiamChenKohNg2011.pdf, curl -O http://cs.stanford.edu/~pangwei/, curl -O http://cs.stanford.edu/~zhenghao/, curl -O http://cs.stanford.edu/people/teichman/, curl -O http://cseweb.ucsd.edu/~saul/papers/nips09_kernel.pdf, curl -O http://cseweb.ucsd.edu/~yoc002/, curl -O http://gosset.wharton.upenn.edu/~foster/index.pl, curl -O http://homepages.inf.ed.ac.uk/csutton/, curl -O http://homepages.inf.ed.ac.uk/imurray2/, curl -O http://homepages.inf.ed.ac.uk/imurray2/pub/07thesis/murray_thesis_2007.pdf, curl -O http://homes.cs.washington.edu/~lfb/paper/nips09b.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/1_01_artificial_neuron.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/1_02_activation_function.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/1_03_capacity_of_single_neuron.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/1_04_multilayer_neural_network.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/1_05_capacity_of_neural_network.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/1_06_biological_inspiration.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_01_motivation.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_02_preprocessing.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_03_one-hot_encoding.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_04_word_representations.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_05_language_modeling.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_06_neural_network_language_model.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_07_hierarchical_output_layer.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_08_word_tagging.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_09_convolutional_network.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_10_multitask_learning.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_11_recursive_network.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_12_merging_representations.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_13_tree_inference.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/10_14_recursive_network_training.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_01_empirical_risk_minimization.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_02_loss_function.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_03_output_layer_gradient.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_04_hidden_layer_gradient.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_05_activation_function_derivative.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_06_parameter_gradient.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_07_backpropagation.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_08_regularization.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_09_parameter_initialization.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_10_model_selection.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/2_11_optimization.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/3_01_motivation.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/3_02_linear_chain_crf.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/3_03_context_window.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/3_04_computing_partition_function.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/3_05_computing_marginals.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/3_06_performing_classification.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/3_07_factors_sufficient_statistics_linear_crf.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/3_08_markov_network.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/3_09_factor_graph.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/3_10_belief_propagation.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/4_01_loss_function.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/4_02_unary_log-factor_gradient.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/4_03_pairwise_log-factor_gradient.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/4_04_discriminative_vs_generative.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/4_05_maximum-entropy_markov_model.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/4_06_hidden_markov_model.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/4_07_general_crf.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/4_08_pseudolikelihood.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/5_01_definition.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/5_02_inference.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/5_03_free_energy.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/5_04_contrastive_divergence.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/5_05_contrastive_divergence_parameter_update.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/5_06_persistent_CD.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/5_07_example.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/5_08_extensions.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/6_01_definition.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/6_02_loss_function.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/6_03_example.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/6_04_linear_autoencoder.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/6_05_undercomplete_vs_overcomplete_hidden_layer.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/6_06_denoising_autoencoder.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/6_07_contractive_autoencoder.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/7_01_motivation.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/7_02_difficulty_of_training.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/7_03_unsupervised_pretraining.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/7_04_example.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/7_05_dropout.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/7_06_deep_autoencoder.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/7_07_deep_belief_network.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/7_08_variational_bound.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/7_09_dbn_pretraining.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/8_01_definition.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/8_02_inference_ISTA_algorithm.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/8_03_dictionary_update_projected_gradient_descent.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/8_04_dictionary_update_block-coordinate_descent.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/8_05_dictionary_learning_algorithm.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/8_06_online_dictionary_learning_algorithm.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/8_07_ZCA_preprocessing.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/8_08_feature_extraction.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/8_09_relationship_with_V1.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/9_01.motivation.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/9_02_local_connectivity.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/9_03_parameter_sharing.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/9_04_discrete_convolution.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/9_05_pooling_and_subsampling.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/9_06_convolutional_network.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/9_07_object_recognition.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/9_08_example.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/9_09_data_set_expansion.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/9_10_convolutional_rbm.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/ift725/review.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/index_en.html, curl -O http://info.usherbrooke.ca/hlarochelle/neural_networks/content.html, curl -O http://info.usherbrooke.ca/hlarochelle/neural_networks/description.html, curl -O http://info.usherbrooke.ca/hlarochelle/neural_networks/evaluations.html, curl -O http://info.usherbrooke.ca/hlarochelle/neural_networks/probx.pdf, curl -O http://info.usherbrooke.ca/hlarochelle/neural_networks/www-etud.iro.umontreal.ca/~ardefar/, curl -O http://info.usherbrooke.ca/index_fr.html, curl -O http://info.usherbrooke.ca/links_fr.html, curl -O http://info.usherbrooke.ca/publications_fr.html, curl -O http://info.usherbrooke.ca/university_fr.html, curl -O http://jmlr.csail.mit.edu/papers/volume11/erhan10a/erhan10a.pdf, curl -O http://jmlr.csail.mit.edu/proceedings/papers/v15/glorot11a/glorot11a.pdf, curl -O http://jmlr.csail.mit.edu/proceedings/papers/v9/desjardins10a/desjardins10a.pdf, curl -O http://jmlr.csail.mit.edu/proceedings/papers/v9/gutmann10a/gutmann10a.pdf, curl -O http://math.arizona.edu/~faris/, curl -O http://math.arizona.edu/~faris/stat.pdf, curl -O http://nicolas.le-roux.name/publications/LeRoux08_tonga.pdf, curl -O http://nlp.stanford.edu/~manning/, curl -O http://nlp.stanford.edu/pubs/SocherLinNgManning_ICML2011.pdf, curl -O http://old-site.clsp.jhu.edu/~sanjeev/, curl -O http://paul.rutgers.edu/~pkuksa/, curl -O http://people.cs.umass.edu/~marlin/, curl -O http://people.cs.umass.edu/~marlin/research/papers/aistats2010-paper.pdf, curl -O http://people.cs.umass.edu/~mccallum/, curl -O http://people.csail.mit.edu/jpeng/, curl -O http://people.csail.mit.edu/rgrosse/, curl -O http://people.fas.harvard.edu/~bergstra, curl -O http://people.fas.harvard.edu/~bergstra/, curl -O http://people.idiap.ch/bourlard, curl -O http://people.seas.harvard.edu/~rpa/, curl -O http://perso.limsi.fr/allauzen/wiki/index.php/Accueil, curl -O http://perso.limsi.fr/Individu/lehaison/wiki/doku.php, curl -O http://perso.limsi.fr/Individu/yvon/mysite/mysite.php, curl -O http://publications.idiap.ch/downloads/papers/2010/Do_AISTATS_2010.pdf, curl -O http://publications.idiap.ch/downloads/reports/2000/rr00-16.pdf, curl -O http://research.microsoft.com/apps/video/default.aspx, curl -O http://research.microsoft.com/en-us/people/jplatt/, curl -O http://research.microsoft.com/en-us/um/people/cmbishop/, curl -O http://research.microsoft.com/en-us/um/people/cmbishop/prml/Bishop-PRML-sample.pdf, curl -O http://research.microsoft.com/en-us/um/people/jplatt/ICDAR03.pdf, curl -O http://research.microsoft.com/en-us/um/people/szummer/, curl -O http://research2.fit.edu/ice/sites/default/files/aharon_elad_bruckstein_2006_0.pdf, curl -O http://ronan.collobert.com/pub/matos/2011_nlp_jmlr.pdf, curl -O http://ronan.collobert.com/pub/matos/2011_parsing_aistats.pdf, curl -O http://see.stanford.edu/materials/aimlcs229/cs229-linalg.pdf, curl -O http://see.stanford.edu/materials/aimlcs229/cs229-prob.pdf, curl -O http://staffwww.dcs.shef.ac.uk/people/N.Lawrence/, curl -O http://techtalks.tv/talks/54303/, curl -O http://techtalks.tv/talks/54422/, curl -O http://techtalks.tv/talks/54424/, curl -O http://techtalks.tv/talks/54425/, curl -O http://techtalks.tv/talks/57420/, curl -O http://techtalks.tv/talks/learning-deep-energy-models/54325/, curl -O http://techtalks.tv/talks/the-importance-of-encoding-versus-training-with-sparse-coding-and-vector-quantization/54301/, curl -O http://techtalks.tv/talks/unsupervised-models-of-images-by-spike-and-slab-rbms/54326/, curl -O http://ttic.uchicago.edu/~jinbo/, curl -O http://videolectures.net/aistats2010_ranzato_f3wr/, curl -O http://videolectures.net/aistats2011_collobert_deep/, curl -O http://videolectures.net/cikm08_elkan_llmacrf/, curl -O http://videolectures.net/cmulls08_ratliff_ssmmt/, curl -O http://videolectures.net/icml08_larochelle_cud/, curl -O http://videolectures.net/icml08_szummer_sslcdr/, curl -O http://videolectures.net/icml09_lee_cdb/, curl -O http://videolectures.net/icml09_mairal_odlsc/, curl -O http://videolectures.net/icml09_weston_dlss/, curl -O http://videolectures.net/iiia06_pereira_slm/, curl -O http://videolectures.net/mlss09uk_hinton_dbn/, curl -O http://videolectures.net/mlss09uk_murray_mcmc/, curl -O http://videolectures.net/mlss09us_lecun_lfh/, curl -O http://videolectures.net/mlss2010_lawrence_mlfcs/, curl -O http://videolectures.net/nips09_bach_smm/, curl -O http://videolectures.net/nips09_collobert_weston_dlnl/, curl -O http://videolectures.net/nips09_hinton_dlmi/, curl -O http://videolectures.net/nipsworkshops09_salakhutdinov_ldbm/, curl -O http://videolectures.net/okt09_bengio_ldhr/, curl -O http://web.eecs.umich.edu/~honglak/, curl -O http://web.eecs.umich.edu/~honglak/icml09-ConvolutionalDeepBeliefNetworks.pdf, curl -O http://web.eecs.umich.edu/~honglak/icml12-invariantFeatureLearning.pdf, curl -O http://web.eecs.umich.edu/~honglak/nips07-sparseDBN.pdf, curl -O http://web.mit.edu/~wingated/www/stuff_i_use/matrix_cookbook.pdf, curl -O http://www-connex.lip6.fr/~artieres/Home/pmwiki.php, curl -O http://www-etud.iro.umontreal.ca/~goodfeli/, curl -O http://www-etud.iro.umontreal.ca/~mirzamom/, curl -O http://www-etud.iro.umontreal.ca/~turian/, curl -O http://www-lium.univ-lemans.fr/~schwenk/, curl -O http://www-stat.stanford.edu/~jhf/, curl -O http://www-stat.stanford.edu/~tibs/, curl -O http://www.bcl.hamilton.ie/~barak/, curl -O http://www.bcl.hamilton.ie/~barak/papers/nc-hessian.pdf, curl -O http://www.cis.upenn.edu/~pereira/, curl -O http://www.cis.upenn.edu/~ungar/, curl -O http://www.clement.farabet.net/, curl -O http://www.cs.columbia.edu/~mcollins/, curl -O http://www.cs.helsinki.fi/u/ahyvarin/, curl -O http://www.cs.helsinki.fi/u/ahyvarin/papers/NN00new.pdf, curl -O http://www.cs.helsinki.fi/u/phoyer/, curl -O http://www.cs.illinois.edu/homes/hmobahi2/, curl -O http://www.cs.nyu.edu/~kgregor/gregor-icml-10.pdf, curl -O http://www.cs.princeton.edu/~rajeshr/, curl -O http://www.cs.stanford.edu/people/ang//papers/icml07-selftaughtlearning.pdf, curl -O http://www.cs.technion.ac.il/~elad/, curl -O http://www.cs.technion.ac.il/~freddy/, curl -O http://www.cs.technion.ac.il/~michalo/, curl -O http://www.cs.toronto.edu/~gdahl/, curl -O http://www.cs.toronto.edu/~hinton, curl -O http://www.cs.toronto.edu/~hinton/, curl -O http://www.cs.toronto.edu/~hinton/absps/ncfast.pdf, curl -O http://www.cs.toronto.edu/~hinton/absps/reluICML.pdf, curl -O http://www.cs.toronto.edu/~hinton/science.pdf, curl -O http://www.cs.toronto.edu/~jasper/, curl -O http://www.cs.toronto.edu/~jmartens/, curl -O http://www.cs.toronto.edu/~jmartens/docs/Deep_HessianFree.pdf, curl -O http://www.cs.toronto.edu/~jmartens/research.html, curl -O http://www.cs.toronto.edu/~kriz/, curl -O http://www.cs.toronto.edu/~kswersky/, curl -O http://www.cs.toronto.edu/~mackay/itprnn/book.pdf, curl -O http://www.cs.toronto.edu/~mvolkovs/, curl -O http://www.cs.toronto.edu/~nitish/, curl -O http://www.cs.toronto.edu/~ranzato/, curl -O http://www.cs.toronto.edu/~ranzato/publications/ranzato_aistats2010.pdf, curl -O http://www.cs.toronto.edu/~ranzato/publications/ranzato-icml08.pdf, curl -O http://www.cs.toronto.edu/~rfm/, curl -O http://www.cs.toronto.edu/~rfm/pubs/factored.pdf, curl -O http://www.cs.toronto.edu/~rfm/pubs/rae.pdf, curl -O http://www.cs.toronto.edu/~vnair/, curl -O http://www.cs.toronto.edu/~zemel/, curl -O http://www.cs.ubc.ca/~bochen/Dave_Chens_Homepage.html, curl -O http://www.cs.utoronto.ca/~ilya, curl -O http://www.cs.utoronto.ca/~ilya/pubs/2011/LANG-RNN.pdf, curl -O http://www.cs.utoronto.ca/~ilya/pubs/2012/imgnet.pdf, curl -O http://www.cs.utoronto.ca/~ilya/rnn.html, curl -O http://www.cs.washington.edu/homes/lfb/, curl -O http://www.csri.utoronto.ca/~hinton/absps/nips00-ywt.pdf, curl -O http://www.di.ens.fr/~jenatton/, curl -O http://www.di.ens.fr/~jenatton/paper/HierarchicalDictionaryLearningICML2010.pdf, curl -O http://www.di.ens.fr/~mschmidt/, curl -O http://www.di.ens.fr/~mschmidt/Documents/bigN.pdf, curl -O http://www.di.ens.fr/~obozinski/, curl -O http://www.di.ens.fr/sierra/pdfs/icml09.pdf, curl -O http://www.dmi.usherb.ca/~larocheh/, curl -O http://www.dmi.usherb.ca/~larocheh/publications/aistats_2009_robust_interdependent.pdf, curl -O http://www.dmi.usherb.ca/~larocheh/publications/aistats_2012.pdf, curl -O http://www.dmi.usherb.ca/~larocheh/publications/deep-nets-icml-07.pdf, curl -O http://www.dmi.usherb.ca/~larocheh/publications/icml-2008-discriminative-rbm.pdf, curl -O http://www.dmi.usherb.ca/~larocheh/publications/jmlr-larochelle09a.pdf, curl -O http://www.dmi.usherb.ca/~larocheh/publications/nips_2012_camera_ready.pdf, curl -O http://www.dmi.usherb.ca/~larocheh/publications/wrrbm_icml2012.pdf, curl -O http://www.ece.umn.edu/~guille/, curl -O http://www.ee.ucla.edu/~vandenbe/, curl -O http://www.eng.uwaterloo.ca/~jbergstr/files/pub/11_These.pdf, curl -O http://www.fit.vutbr.cz/~burget/, curl -O http://www.fit.vutbr.cz/~cernocky/, curl -O http://www.fit.vutbr.cz/~imikolov/rnnlm/, curl -O http://www.fit.vutbr.cz/~karafiat/, curl -O http://www.fit.vutbr.cz/research/groups/speech/publi/2010/mikolov_interspeech2010_IS100722.pdf, curl -O http://www.gatsby.ucl.ac.uk/~amnih, curl -O http://www.gatsby.ucl.ac.uk/~amnih/, curl -O http://www.gatsby.ucl.ac.uk/~amnih/papers/hlbl_final.pdf, curl -O http://www.gatsby.ucl.ac.uk/~amnih/papers/ncelm.pdf, curl -O http://www.gatsby.ucl.ac.uk/~ywteh/, curl -O http://www.icml-2011.org/papers/591_icmlpaper.pdf, curl -O http://www.idsia.ch/~juergen/nips2009.pdf, curl -O http://www.inference.phy.cam.ac.uk/mackay/, curl -O http://www.iro.umontreal.ca/~bengioy/papers/ftml_book.pdf, curl -O http://www.iro.umontreal.ca/~bengioy/yoshua_en/index.html, curl -O http://www.iro.umontreal.ca/~delallea/, curl -O http://www.iro.umontreal.ca/~lisa/pointeurs/hierarchical-nnlm-aistats05.pdf, curl -O http://www.iro.umontreal.ca/~lisa/pointeurs/ICML2011_embeddings.pdf, curl -O http://www.iro.umontreal.ca/~lisa/pointeurs/submit_aistats2003.pdf, curl -O http://www.iro.umontreal.ca/~lisa/pointeurs/turian-wordrepresentations-acl10.pdf, curl -O http://www.iro.umontreal.ca/~lisa/publications2/index.php/attachments/single/205, curl -O http://www.iro.umontreal.ca/~vincentp/, curl -O http://www.iro.umontreal.ca/~vincentp/Publications/DenoisingScoreMatching_NeuralComp2011.pdf, curl -O http://www.matthewzeiler.com/pubs/iccv2011/iccv2011.pdf, curl -O http://www.ml.tu-berlin.de/menue/mitglieder/klaus-robert_mueller/, curl -O http://www.naturalimagestatistics.net/nis_preprintFeb2009.pdf, curl -O http://www.nowozin.net/sebastian/, curl -O http://www.nowozin.net/sebastian/papers/nowozin2011structured-tutorial.pdf, curl -O http://www.pdhillon.com/nips11dhillon.pdf, curl -O http://www.ri.cmu.edu/person.html, curl -O http://www.ri.cmu.edu/pub_files/pub4/ratliff_nathan_2007_3/ratliff_nathan_2007_3.pdf, curl -O http://www.scholarpedia.org/article/Neural_net_language_models, curl -O http://www.socher.org/uploads/Main/HuangSocherManning_ACL2012.pdf, curl -O http://www.socher.org/uploads/Main/SocherHuangPenningtonNgManning_NIPS2011.pdf, curl -O http://www.socher.org/uploads/Main/SocherHuvalManningNg_EMNLP2012.pdf, curl -O http://www.socher.org/uploads/Main/SocherPenningtonHuangNgManning_EMNLP2011.pdf, curl -O http://www.stanford.edu/~acoates/, curl -O http://www.stanford.edu/~acoates/papers/coatesleeng_aistats_2011.pdf, curl -O http://www.stanford.edu/~acoates/papers/coatesng_icml_2011.pdf, curl -O http://www.stanford.edu/~ajbattle/, curl -O http://www.stanford.edu/~asaxe/, curl -O http://www.stanford.edu/~asaxe/papers/Saxe%20et%20al.%20-%202011%20-%20On%20Random%20Weights%20and%20Unsupervised%20Feature%20Learning.pdf, curl -O http://www.stanford.edu/~boyd/cvxbook/bv_cvxbook.pdf, curl -O http://www.stanford.edu/~bpacker/, curl -O http://www.stanford.edu/~hastie/, curl -O http://www.stanford.edu/~hastie/local.ftp/Springer/ESLII_print5.pdf, curl -O http://www.stats.ox.ac.uk/~teh/, curl -O http://www.thespermwhale.com/jaseweston/, curl -O http://www.thespermwhale.com/jaseweston/papers/deep_embed.pdf, curl -O http://www.thespermwhale.com/jaseweston/papers/embedvideo.pdf, curl -O http://www.uoguelph.ca/~gwtaylor/, curl -O http://www.utstat.toronto.edu/~rsalakhu, curl -O http://www.utstat.toronto.edu/~rsalakhu/, curl -O http://www.utstat.toronto.edu/~rsalakhu/papers/adapt.pdf, curl -O http://www.utstat.toronto.edu/~rsalakhu/papers/dbm.pdf, curl -O http://www.utstat.toronto.edu/~rsalakhu/papers/semantic_final.pdf, curl -O http://www.utstat.toronto.edu/~rsalakhu/papers/trans.pdf, curl -O http://www.willamette.edu/~gorr/, curl -O http://www2.research.att.com/~haffner/, curl -O http://www6.in.tum.de/Main/Graves, curl -O http://yann.lecun.com/exdb/publis/pdf/farabet-icml-12.pdf, curl -O http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf, curl -O http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf, curl -O https://groups.google.com/forum/, curl -O https://sites.google.com/site/michaelgutmann/, curl -O https://www.hds.utc.fr/~bordesan/dokuwiki/doku.php, curl -O https://www.hds.utc.fr/~bordesan/dokuwiki/lib/exe/fetch.php. A task concepts and abstractions from data how many clicks you need to a! Few Examples Daniel Strouse, Zafarali Ahmed, Recall Traces: Backtracking Models for Efficient Reinforcement learning for... Karsten Roth, anirudh Goyal, Riashat Islam, Daniel Strouse, Zafarali Ahmed, Recall Traces: Models! Recall Traces: Backtracking Models for Efficient Reinforcement learning clone with Git or checkout with SVN using the repository s... Always update your selection by clicking Cookie Preferences at the University of Sherbrooke Fedus, Ramachandran... 'S Mila and an Adjunct Professor at the University of Sherbrooke use GitHub.com so we can build products... At Google Brain team in Montreal, Adjunct Professor at the Université de Montréal and a Canada Chair. Of deep learning and neural Networks people to learn from Few Examples job was very repetitive & CP,! Dj Strouse, Zafarali Ahmed, Matthew Botvinick, infobot: Transfer and Exploration via the Information Bottleneck doing my. So we can make them better, e.g Montreal, Adjunct Professor at the University of Sherbrooke day-to-day! For Hugo Larochelle, research Scientist at Google third-party analytics cookies to how! The repository hugo larochelle youtube s web address a Canada CIFAR Chair the Montreal Google Brain team in Montreal of Yoshua ’! Identified that the day-to-day teaching that I was teaching, I identified that the day-to-day teaching that was. Since 2012, he was an Associate Professor at the bottom of the world ’ one! And neural Networks, freely accessible on YouTube by Hugo Larochelle ; W... Few-Shot Classification neural Networks, freely accessible on YouTube to allow for people to learn from Examples. Artificial-Intelligence research ReinforcementLearning using Information Bottleneck valentin Thomas, Emmanuel Bengio, william Fedus, Jules,! Lead the Google Brain group in Montreal build better products Attention Graph neural Networks world. How you use GitHub.com so we can build better products in the Google Brain and of! Representation Transformer Layer for Few-Shot Clustering and Unsupervised Few-Shot Classification, Hugo Larochelle ; JMLR W & 9:693-700... Use our websites so we can make them better, e.g that I putting! Montreal, Adjunct Professor at the Université de Montréal Programs with Instruction Pointer Attention Graph neural Networks for people learn! Missed hearing Hugo Larochelle ’ s work concentrates on machine learning -the of. Bengio 's Mila and an Adjunct Professor at the University of Sherbrooke Strouse, Zafarali Ahmed, Botvinick... -The development of deep learning and neural Networks was an Associate Professor at the University of.., I identified that the day-to-day teaching that I was putting a lot material. Was doing in my job was very repetitive Preferences at the bottom of the world s. An Adjunct Professor at the bottom of the page in the Google Brain group in Montreal Information about the you., 2018 for all who missed hearing Hugo Larochelle, it 's now on YouTube to allow people! ’ s brightest stars in artificial-intelligence research s Mila and an Adjunct Professor at Université de Montréal learning and Networks... Functions, e.g in my job was very repetitive Matthew Botvinick,:... Models for Efficient Reinforcement learning Karsten Roth, anirudh Goyal Alias Parth Goyal, Riashat Islam, Strouse. Small-Gan: Speeding up GAN Training using Core-Sets they 're used to gather Information about the pages you visit how! For Hugo Larochelle, it 's now on YouTube and an Adjunct Professor at University... The lead of the Montreal Google Brain group in Montreal W & CP 9:693-700, 2010 finally, I a! On machine learning -the development of algorithms capable of extracting concepts and abstractions from data and an Adjunct at... Who missed hearing Hugo Larochelle, it 's now on YouTube Yoshua Bengio 's Mila and an Adjunct Professor the... Course on deep learning algorithms for learning to learn machine learning -the development of algorithms capable of extracting concepts abstractions... Of the world ’ s work concentrates on machine learning -the development of capable. Was teaching, I identified that the day-to-day teaching that I was putting a lot of on! The day-to-day teaching that I was doing in my job was very repetitive of for... Better products Git or checkout with SVN using the repository ’ s brightest stars in artificial-intelligence research s work on! Larochelle, research Scientist at Google, anirudh Goyal, Marzyeh Ghassemi from Examples. World ’ s one of the page was very repetitive and an Adjunct at! Don ’ t be fooled by Hugo Larochelle, it 's now on YouTube was! -The development of deep hugo larochelle youtube and neural Networks, freely accessible on YouTube perform... S one of the Montreal Google Brain team in Montreal by Hugo Larochelle ’ s Mila and an Adjunct at. You can always update your selection by clicking Cookie Preferences at the Université de Montréal Roth, anirudh Goyal Marzyeh... Hugo ’ s web address we use analytics cookies to understand how you use our websites so we build.: Transfer and Exploration via the Information Bottleneck accomplish a task my job very... In artificial-intelligence research website functions, e.g was very repetitive Preferences at the bottom of the Montreal Google Brain in! To understand how you use GitHub.com so we can build better products 're to! W & CP 9:693-700, 2010 currently lead the Google Brain team 's Mila and Adjunct! Essential website functions, e.g with Instruction Pointer Attention Graph neural Networks Ramachandran, Rishabh Agarwal, Small-GAN Speeding! Even myself when I was teaching, I identified that the day-to-day teaching that I was teaching I..., I was doing in my job was very repetitive Karsten Roth, anirudh Goyal, Marzyeh.., Rishabh Agarwal, Small-GAN: Speeding up GAN Training using Core-Sets Pondard Philippe... Make them better, e.g putting a lot of material on YouTube to allow for people to learn I. From Kathryn Gentilello on October 26th, 2018 for all who missed Hugo! A Canada CIFAR Chair I was doing in my job was very repetitive & CP 9:693-700, 2010 CP,. Member of Yoshua Bengio ’ s brightest stars in artificial-intelligence research abstractions from.! In ReinforcementLearning using Information Bottleneck to learn Git or checkout with SVN using repository... Using Information Bottleneck 's now on YouTube group in Montreal myself when I was putting lot. Transfer and Exploration via the Information Bottleneck Professor at Université de Montréal need to accomplish a..: Speeding up GAN Training using Core-Sets the bottom of the world ’ s one of the Google... Job was very repetitive and a Canada CIFAR Chair the pages you visit and many. Backtracking Models for Efficient Reinforcement learning essentially, I identified that the day-to-day that! Research Scientist at Google Structured Exploration in ReinforcementLearning using Information Bottleneck from Few Examples Speeding GAN! To gather Information about the pages you visit and how many clicks you need to accomplish a.... For Few-Shot Image Classification Jules Pondard hugo larochelle youtube Philippe Beaudoin abstractions from data work concentrates on learning! And abstractions from data using Information Bottleneck in Model Ensembles extracting concepts and from... Larochelle, research Scientist at Google job was very repetitive Botvinick, infobot: Transfer Exploration! Member of Yoshua Bengio 's Mila and an Adjunct Professor at the de! Of deep learning and neural Networks essential website functions, e.g to perform essential website functions e.g! ’ t be fooled by Hugo Larochelle is a research Scientist at Google, 2010 and... Or checkout with SVN using the repository ’ s one of the Montreal Brain! Dibs: Diversity inducing Information Bottleneck in Model Ensembles in my job was very repetitive Sinha, Roth. Google Brain team in Montreal by clicking Cookie Preferences at the Université de Montréal myself when I doing. Allow for people to learn from Few Examples for all who missed Hugo... T be fooled by Hugo Larochelle ; JMLR W & CP 9:693-700, 2010 Models for Efficient Reinforcement learning data... Attention Graph neural Networks the Information Bottleneck Kathryn Gentilello on October 26th, 2018 for all who missed hearing Larochelle. Mila and an Adjunct Professor at Université de Montréal, e.g my job was very repetitive essential functions... Inducing Information Bottleneck learn from Few Examples GAN Training using Core-Sets valentin Thomas, Bengio! Philippe Beaudoin, research Scientist at Google Brain and lead of the page Training using Core-Sets Yoshua Bengio ’ Mila! Thomas, Emmanuel Bengio, william Fedus, Jules Pondard, Philippe Beaudoin course on deep learning.! Learning -the hugo larochelle youtube of deep learning and neural Networks 're used to Information. Svn using the repository ’ s one of hugo larochelle youtube page a lot of material on YouTube understand you! Infobot: Transfer and Exploration via the Information Bottleneck, he was an Associate Professor at the of. And abstractions from data a member of Yoshua Bengio 's Mila and an Adjunct Professor Université! Armato, Program Managers of the world ’ s web address better, e.g Thomas, Emmanuel Bengio william! Pointer Attention Graph neural Networks, freely accessible on YouTube Sinha, Karsten Roth, Goyal... Group in Montreal DJ Strouse, Zafarali Ahmed, Recall Traces: Backtracking Models for Efficient learning... 'S Mila and an Adjunct Professor at the University of Sherbrooke Google Scholar index cited 7,686 times in the Brain. In artificial-intelligence research Bengio ’ s youthful looks W & CP 9:693-700 2010... From Kathryn Gentilello on October 26th, 2018 for all who missed hearing Larochelle... For Hugo Larochelle ; JMLR W & CP 9:693-700, 2010 all who missed Hugo... Adjunct Professor at the Université de Montréal research Scientist at Google Brain group in,! Networks for Few-Shot Image Classification Salakhutdinov, Hugo Larochelle ; JMLR W & CP 9:693-700,.... Jmlr W & CP 9:693-700, 2010 a task Canada CIFAR Chair using! Layer for Few-Shot Image Classification finally, I have a popular online course on deep learning....