Nos « Tea Talks »

Nos « tea talks » sont des présentations au sujet de l’apprentissage automatique faites par un(e) étudiant(e) de Mila ou un(e) invité(e). Ces conférences ont généralement lieu le vendredi à 10 h 30 et sont ouvertes au public.

Si vous souhaitez donner un « tea talk », veuillez envoyer un courriel à  .

Si vous souhaitez vous abonner à nos listes de diffusion et être informé de toutes les conférences à venir, veuillez envoyer un courriel à

L’horaire des conférences précédentes et à venir ainsi que certaines des diapositives des présentations sont disponibles ci-dessous.

https://sites.google.com/lisa.iro.umontreal.ca/tea-talk-recordings/home

Dates [M/D/Y]
Time
Speaker
Place
Title
Fri January 11 201910h30Maxime Chevalier-BoisvertMila AuditoriumBabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Fri January 25 201910h30Hugo LarochelleMila Auditorium(Part II) Few-Shot Learning with Meta-Learning: Progress Made and Challenges Ahead
Fri February 1 201910h30Isabela AlbuquerqueMila AuditoriumMulti-objective training of Generative Adversarial Networks with multiple discriminators
Fri March 8 201910h30David BleiMila AuditoriumThe Blessings of Multiple Causes
Fri March 15 2019
Fri 22 March 2019
Fri 29 March 201910h30Jeffrey PenningtonMila AuditoriumAre Overparameterized Neural Networks Actually Just Linear Models?
Fri 5 April 201910h30Anirudh GoyalMila AuditoriumInductive Biases, Invariances and Generalization
Fri 12 April 201910h30Yoshua BengioMila AuditoriumMeta-transfer learning for factorizing representations and knowledge for AI
Fri 19 April 201910h 30Dhruva RamanMila AuditoriumFundamental Bounds on Learning Performance in Neural Circuits
Fri 3 May 201910h30ICLR Lightning talksMila AuditoriumICLR Lightning Talks
Fri 17 May 201910h30Dan SodicksonAuditorium H2Machine Learning and Medicine: How AI will change the way we see patients, and the way we see ourselves.
Fri 24 May 201910h30Marc BelleMare and Pieter AbeelMila AuditoriumPart 1 : Some progress on understanding the benefits of distributional reinforcement learning, Part 2 : Model-based RL with Meta-Model-Free RL
Fri 31 May 201910h30Liam LiMila AuditoriumRandom Search and Reproducibility for Neural Architecture Search
Fri 21 June 201910h30Guy WolfMila AuditoriumGeometry-based Data Exploration
Fri 28 June 201910h30Audrey DurandMila AuditoriumBandits in the wild
Fri 5 July 201910h30Ankseh Anand and Evan RacahMila AuditoriumUnsupervised State Representation Learning in Atari
Fri 12 July 201910h30Ravindran BalaramanMila AuditoriumReinforcement Learning at Work.
Fri 19 July 201910h30Paul CisekMila AgoraRethinking behavior from an evolutionary perspective
Fri 9 August10h30Leila WehbeMila AgoraUsing insights from the human brain to interpret and improve NLP models
Fri 16 August10h30Andre BarretoMila AgoraEfficient Reinforcement Learning with Generalized Policy Updates
Fri 23 August10h30Laurent Dinh
Fri 30 August10h30Aaditya Ramdas
Fri 13 September10h30Matthew AmodioMila AgoraConstraining GANs in Unsupervised Domain Translation

Diapositives disponibles