- Lisa_teatalk - mailman.iro.umontreal.ca

[Tea Talk] Anne Churchland (Cold Spring Harbor Laboratory) June 29 2018 10:30 AA3195
by Michael Noukhovitch 29 Jui '18

29 Jui '18

This week we have *Anne Churchland * from * Cold Spring Harbor Laboratory * giving a talk on *June 29 2018* at *10:30* in room *AA3195* This talk may be streamed as usual here <https://mila.bluejeans.com/1365483656/webrtc> And you can sign up to meet the speaker here <https://calendar.google.com/calendar/selfsched?sstoken=UVBVTVF0X25Nd09LfGRl…> Don't even think about it! Decide to come to the tea talk and let your feet spontaneously guide the way. Michael *TITLE* Spontaneous movements dominate cortical activity during sensory-guided decision making *KEYWORDS *neuroscience, decision-making, neuro-imaging *ABSTRACT* Animals continually produce a wide array of spontaneous and learned movements and undergo rapid internal state transitions. Most work in neuroscience ignores this “internal backdrop” and instead focuses on neural activity aligned to task-imposed variables such as sensory stimuli. We sought to understand the joint effects of internal backdrop vs. task-imposed variables. We measured neural activity using calcium imaging via a widefield macroscope during decision-making. Surprisingly, the impact of the internal backdrop dwarfed task-imposed sensory and cognitive signals. This dominance was comparable in novice and expert decision-makers and was even stronger in single neuron measurements from frontal cortex. These results highlight spontaneous and learned movements as the main determinant of large-scale cortical activity. By leveraging a wide array of animal movements, our model offers a very general method for separating the impact of internal backdrop from task-imposed neural activity. *BIO* Anne K. Churchland received her Ph.D. in neuroscience from the University of California, San Francisco, advised by Dr. Stephen Lisberger. She then did a postdoctoral fellowship with Dr. Michael Shadlen at the University of Washington in the Physiology and Biophysics Department. Her postdoctoral work focused on mechanisms of decision making in nonhuman primates and included both experimental and theoretical work. The latter was funded by a Pathways to Independence (K99) Award from the National Eye Institute. In 2010, she became an assistant professor at Cold Spring Harbor Laboratory. In starting her own laboratory, Professor Churchland began studying decision making using rodent models to take advantage of emerging tools for circuit dissection which are readily available in rodents. Since then, her laboratory has been a major player in bringing behavioral paradigms to rodents that have been successful in elucidating neural mechanisms in primates. These include perceptual decision making and multisensory integration. Most recently, she has teamed up with other 20 other researchers to for the International Brain Laboratory, a collaboration between theorists and experimentalists aiming to understand the neural computations supporting decision-making. Since joining Cold Spring Harbor Laboratory, Professor Churchland has been the recipient of awards from the McKnight Foundation, the Pew Charitable Trusts, the Klingenstein-Simons Foundation, the Simons Collaboration on the Global Brain, the John Merck Fund and the Chapman Foundations. In addition to her scientific work, Professor Churchland runs science outreach activities at public schools and co-directed the Undergraduate Research Program at Cold Spring Harbor Laboratory. She also maintains a blog about neuroscience research that is directed at a mainstream audience; its recent focus is on reviewing papers on the preprint server. Professor Churchland also funded anneslist.net, a resource highlighting women in systems and computational neuroscience. She received the 2017 Louise Hanson Marshall Special Recognition Award from the Society for Neuroscience for promoting diversity in the field and the 2012 Janett Rosenberg Trubatch Career Development Award for creativity in research prior to tenure.

3 5

[Tea Talk] Dzmitry Bahadanau (MILA) Fri June 22 10:30AM AA3195
by Michael Noukhovitch 22 Jui '18

22 Jui '18

This week we have our very own *Dzmitry Bahadanau* giving a talk on work he did on internship at DeepMind on *Friday June 22* at *10:30AM* in room *AA3195*. Help Dima get a human baseline for instruction following and *come to the tea talk* Michael *TITLE* Learning to Follow Language Instructions with Adversarial Reward Induction *KEYWORDS *language understanding, reinforcement learning, grounded language *ABSTRACT* Recent work has shown that deep reinforcement-learning agents can learn to follow language-like instructions from infrequent environment rewards. However, for many real-world natural language commands that involve a degree of underspecification or ambiguity, such as *tidy the room*, it would be challenging or impossible to program an appropriate reward function. To overcome this, we present a method for learning to follow commands from a training set of instructions and corresponding example goal-states, rather than an explicit reward function. Importantly, the example goal-states are not seen at test time. The approach effectively separates the representation of what instructions require from how they can be executed. In a simple grid world, the method enables an agent to learn a range of commands requiring interaction with blocks and understanding of spatial relations and underspecified abstract arrangements. We further show the method allows our agent to adapt to unseen instructions and changes in the environment without requiring new training examples. *BIO* Dzmitry Bahdanau is a Ph.D. student at the Montreal Institute for Learning Algorithms under the supervision of Yoshua Bengio. His research interest is enabling intelligent assistants that could collaborate with humans and communicate with them in natural language. In the view of this long-term research goal he is interested in language acquisition, language grounding models, reinforcement learning and imitation learning. Dzmitry studied applied mathematics at Belarusian State University in Minsk and obtained his MsC degree in computer science at Jacobs University Bremen, Germany.

1 1

[Tea Talk] Yaroslav Ganin (MILA) Fri June 15 10:30AM AA3195
by Michael Noukhovitch 16 Jui '18

16 Jui '18

This week we have our very own Yaroslav Ganin giving a talk on the work he did on internship at DeepMind on Friday June 15th at 10:30AM in room AA3195 This talk may be streamed as usual here <https://bluejeans.com/809027115/webrtc> And you can sign up to meet the speaker by messaging him on slack If you don't come to the talk, be prepared for a strongly reinforced adversary in the form of me! Michael *TITLE* Synthesizing Programs for Images using Reinforced Adversarial Learning *KEYWORDS *GAN, Reinforcement Learning, Unsupervised Learning *ABSTRACT * Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is where graphics engines may come in handy since they abstract away low-level details and represent images as high-level programs. Current methods that combine deep learning and renderers are limited by hand-crafted likelihood or distance functions, a need for large amounts of supervision, or difficulties in scaling their inference algorithms to richer datasets. To mitigate these issues, we present SPIRAL, an adversarially trained agent that generates a program which is executed by a graphics engine to interpret and sample images. The goal of this agent is to fool a discriminator network that distinguishes between real and rendered data, trained with a distributed reinforcement learning setup without any supervision. A surprising finding is that using the discriminator’s output as a reward signal is the key to allow the agent to make meaningful progress at matching the desired output rendering. To the best of our knowledge, this is the first demonstration of an end-to-end, unsupervised and adversarial inverse graphics agent on challenging real world (MNIST, Omniglot, CelebA) and synthetic 3D datasets

2 3

Fwd: Soutenance de thèse de Caglar Gulcehre
by Michael Noukhovitch 15 Jui '18

15 Jui '18

Forwarding the announcement of Caglar's thesis defense next week *1pm* *Friday June 15 * *AA1360* ---------- Forwarded message --------- From: Pierre McKenzie <mckenzie(a)iro.umontreal.ca> Date: Fri, Jun 8, 2018 at 3:02 PM Subject: Soutenance de thèse de Caglar Gulcehre To: <seminaires(a)iro.umontreal.ca> SOUTENANCE DE THESE DE DOCTORAT Département d'informatique et de recherche opérationnelle Université de Montréal CANDIDAT: Caglar Gulcehre TITRE: Learning and Time: on Using Memory and Curricula for Natural Language Understanding DATE: vendredi 15 juin 2018 HEURE: 13:00 ENDROIT: Local 1360 Pavillon André-Aisenstadt Université de Montréal RÉSUMÉ: In this thesis, I present some of the steps that we took towards advancing natural language understanding and learning long-term dependencies. The goal of those advancements is to keep us on the path to develop better artificial intelligence algorithms by using deep learning based architectures. Deep-learning architectures have a profound effect on various language understanding applications such as summarization, machine translation, language modeling and image caption generation. I will be summarizing five different papers that we have written during my Ph.D In our first article, we propose a novel method to utilize the abundant amount of available monolingual data for training neural machine translation models. We have accomplished this goal by training a long short-term memory (LSTM) language model on a large monolingual corpus first and then fusing the outputs or the hidden representations of the LSTM language model with the decoder of the neural machine translation model which is trained end to end using an attention mechanism. In our second paper, we propose an approach to address the problem of rare words in general for natural language processing tasks. Our approach augments the encoder-decoder architecture with attention model by replacing the softmax layer with our proposed pointer-softmax layer that defines pointers to the source sentences when the decoder predicts. In our third paper, we propose two new approaches to learn alignments in a sequence to sequence model. Our model addresses the difficulty of learning alignments between the source and the target context that arises when the source context is very long. In "Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes," we propose a new approach for augmenting neural networks with an explicit memory mechanism. Our model achieves promising results on question answering and algorithmic tasks. Finally I will conclude with our "Noisy Activation Functions" paper, in which we propose a novel activation function that makes the activations are stochastic by injecting the noise to them. JURY: Président-rapporteur: Pierre McKenzie (DIRO) Directeur de recherche: Yoshua Bengio (DIRO) Membre du jury: Simon Julien-Lacoste (DIRO) Examinateur externe: Christopher Manning (Stanford) Bienvenue à tous. Welcome to all. la présentation sera en anglais.

1 1

[Tea Talk] Maksym Korablyov (MIT) Thr June 7 2018 2:00PM AA3195
by Michael Noukhovitch 07 Jui '18

07 Jui '18

Sorry for the delay but this week we have *Maksym Korablyov * from * MIT * giving a talk on *Thursday June 7 2018* at *2:00PM* in room *AA3195. *This is usually the learning agents' reading group slot so shoutout to them for letting me have this slot and again to Dima for helping put this together. Maksym is interested in meeting with people to discuss RNNs for structural prediction, conditional feature extraction, and 3D object alignment, and also other applications of deep learning to chemistry. Want to meet with him? Sign up here <https://calendar.google.com/calendar/selfsched?sstoken=UVBVTVF0X25Nd09LfGRl…> Can't make it? Email me and I'll set something up! Note: There will be no streaming so come in person! If your *deep learning* code is *breaking bad*, take a break and come to this talk! Michael *TITLE* A few steps towards molecule google *KEYWORDS *deep learning chemistry, deep learning theory *ABSTRACT* Commonly used search engines such as Google can retrieve relevant entries with high speed and accuracy from spaces as big as 10^12 - the number of words in the Internet. Search algorithms that could address the space of 10^80 - 10^100 drug-like molecules are not yet publicly available. The world’s combined effort of pharmaceutical companies (experimental + computational) is ~10^15 molecules/year with 30-50 new drugs found. In this talk I will 1: give some numerical estimates of the value of unexplored chemical space. 2: provide some intuition why all possible molecules could be mapped to a low-dimensional manifold and which families of functions might efficiently describe such mapping. 3: show some empirical results of the search in 10^80. 4: present an algorithm for partial flexible shape match (drug + protein) that we have developed recently. *BIO* Maksym Korablyov is a graduate student advised by Dr. Joseph Jacobson at Massachusetts Institute of Technology, Media Lab. Prior to MIT, Maksym was a Fulbright Fellow at Harvard Medical School with Dr. Gil Alterovitz for one year. Maksym holds MS in Bioinformatics from Georgia Institute of Technology where he developed a series of potent antiviral inhibitors jointly with Dr. James Gumbart and Dr. Raymond Schinazi.

2 1

[Tea Talk] Adrià Recasens (MIT) May 25 2018 1:30 PM AA3195
by Michael Noukhovitch 25 Mai '18

25 Mai '18

For our second talk this Friday, we have *Adrià Recasens * from * MIT *on *Friday May 25 2018* at *1:30 PM* in room *AA3195* This talk will be streamed as usual here: https://bluejeans.com/809027115/webrtc and Adrià is open to meetings but we don't know his schedule after his talk yet, if you're interested in meeting with him, shoot me an email For great research discussions, look no further than this talk! Michael *TITLE* Where are they looking? *KEYWORDS *computer vision *ABSTRACT* Humans have the remarkable ability to follow the gaze of other people to identify what they are looking at. Following eye gaze, or gaze-following, is an important ability that allows us to understand what other people are thinking, the actions they are performing, and even predict what they might do next. Despite the importance of this topic, this problem has only been studied in limited scenarios within the computer vision community. In this talk I will present a deep neural network-based approach for gaze-following. Given an image and the location of a head, our approach follows the gaze of the person and identifies the object being looked at. Furthermore, I will also introduce GazeNet, a deep neural-network to predict the 3D direction of a person's gaze from the full 360 degrees. To complement GazeNet, I will present a novel saliency-based sampling layer for neural networks, the Saliency Sampler, which helps to improve the spatial sampling of input data for an arbitrary task. Our differentiable layer can be added as a preprocessing block to existing task networks and trained altogether in an end-to-end fashion. The effect of the layer is to efficiently estimate how to sample from the original data in order to boost task performance. For example, for the gaze-tracking task in which the original data might range in size up to several megapixels, but where the desired input images to the task network are much smaller, our layer learns how best to sample from the underlying high resolution data in a manner which preserves task-relevant information better than uniform downsampling. *BIO* You can read his bio here: https://people.csail.mit.edu/recasens/

1 2

Fwd: [Lisa_seminaires] [Tea Talk] Nicolas Le Roux (Google) May 25 2018 10:30 AM AA3195
by xavier bouthillier 25 Mai '18

25 Mai '18

He are the slides from Nicolas' talk. ---------- Forwarded message ---------- From: Nicolas Le Roux <nlr(a)google.com> Date: Fri, May 25, 2018 at 10:32 AM Subject: Re: [Lisa_seminaires] [Lisa_teatalk] [Tea Talk] Nicolas Le Roux (Google) May 25 2018 10:30 AM AA3195 To: xavier.bouthillier(a)gmail.com On Fri, 25 May 2018 at 10:16, xavier bouthillier < xavier.bouthillier(a)gmail.com> wrote: > Salut Nicolas, > > Pour le streaming tu peux te connecter à l'adresse suivante: > https://bluejeans.com/809027115/webrtc > On va faire un share-screen pour partager tes slides en temps réel. Je > vais seulement streamer, je n'enregistrerai pas. > > Le local 3195 est ouvert, tu peux venir t'installer quand tu veux. > > Xavier > > On Tue, May 22, 2018 at 12:45 PM, Nicolas Le Roux <nlr(a)google.com> wrote: > >> For those of you who attended my talk at the Workshop on learning theory, >> this one will fill in some of the gaps I mentioned. >> >> On Tue, 22 May 2018 at 12:17, Michael Noukhovitch <mnoukhov(a)gmail.com> >> wrote: >> >>> This week we will have two tea talks (morning and afternoon) on Friday! >>> Wow! >>> >>> The first talk will be *Nicolas Le* *Roux * on *May 25 2018* at *10:30 >>> AM* in room *AA3195* (note the room change, we'll most likely be in >>> 3195 for the summer). >>> >>> Streaming is, as always, at this link: https://bluejeans.com/ >>> 809027115/webrtc but watch it live because there will be no recordings! >>> >>> Don't waver on going to this talk, it is sure to be invariantly >>> excellent! >>> Michael >>> >>> *TITLE* An exploration of variance reduction techniques in stochastic >>> optimization >>> >>> *KEYWORDS *deep learning theory, optimization >>> >>> *ABSTRACT* >>> I will present recent and ongoing work on reducing the variance in >>> stochastic optimization techniques to speed-up and simplify the resulting >>> algorithms. In particular, stochastic gradient methods can suffer from high >>> variance, limiting their convergence speed. While variance reduction >>> techniques exist in the finite case, they are rarer in the online case. We >>> demonstrate how an increasing momentum offers variance reduction in the >>> online case, at the expense of bias, and how that bias can be countered by >>> an extrapolation step. The resulting algorithm differs from iterate >>> averaging in only a factor, but, in the context of the minimization of a >>> quadratic function, this difference is enough to lead to the first >>> algorithm converging both linearly in the noiseless and sublinearly in the >>> homoscedastic noise case when using a constant stepsize. >>> >>> *BIO* >>> *Nicolas Le Roux got an MSc in Applied Maths from Ecole Centrale Paris >>> and an MSc in Maths, Learning and Vision from ENS Cachan. He got his PhD in >>> 2008 from University of Montreal where he worked with Yoshua Bengio on >>> neural networks in general and their optimisation in particular. He then >>> moved to Microsoft Research Cambridge to work on generative models of >>> images with John Winn. In 2010, he joined Inria in Francis Bach's team to >>> work on large-scale convex optimisation. From 2012 to 2017, he created and >>> managed the research team at Criteo in Paris. He joined Google Brain >>> Montreal in 2017 where he now works on large-scale optimization and >>> reinforcement learning.* >>> >>> -- >>> You received this message because you are subscribed to the Google >>> Groups "brain-montreal-office-hours" group. >>> To unsubscribe from this group and stop receiving emails from it, send >>> an email to brain-montreal-office-hours+unsubscribe(a)google.com. >>> To post to this group, send email to brain-montreal-office-hours@ >>> google.com. >>> To view this discussion on the web visit https://groups.google.com/a/ >>> google.com/d/msgid/brain-montreal-office-hours/CAMVr0Vy4KsyukWMA_ >>> 7jfFzebONgVbD3Oh7wa%2Bk5eVxta8KYUVg%40mail.gmail.com >>> <https://groups.google.com/a/google.com/d/msgid/brain-montreal-office-hours/…> >>> . >>> >>> -- >>> You received this message because you are subscribed to the Google >>> Groups "brain-mon-fte" group. >>> To unsubscribe from this group and stop receiving emails from it, send >>> an email to brain-mon-fte+unsubscribe(a)google.com. >>> To post to this group, send email to brain-mon-fte(a)google.com. >>> To view this discussion on the web visit https://groups.google.com/a/ >>> google.com/d/msgid/brain-mon-fte/CAMVr0Vy4KsyukWMA_7jfFzebONgVbD3Oh7wa% >>> 2Bk5eVxta8KYUVg%40mail.gmail.com >>> <https://groups.google.com/a/google.com/d/msgid/brain-mon-fte/CAMVr0Vy4Ksyuk…> >>> . >>> _______________________________________________ >>> Lisa_teatalk mailing list >>> Lisa_teatalk(a)iro.umontreal.ca >>> https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_teatalk >>> >>> -- >>> You received this message because you are subscribed to the Google >>> Groups "brain-montreal-office-hours" group. >>> To unsubscribe from this group and stop receiving emails from it, send >>> an email to brain-montreal-office-hours+unsubscribe(a)google.com. >>> To post to this group, send email to brain-montreal-office-hours@ >>> google.com. >>> To view this discussion on the web visit https://groups.google.com/a/ >>> google.com/d/msgid/brain-montreal-office-hours/CAMVr0Vy4KsyukWMA_ >>> 7jfFzebONgVbD3Oh7wa%2Bk5eVxta8KYUVg%40mail.gmail.com. >>> >>> -- >>> You received this message because you are subscribed to the Google >>> Groups "brain-mon-fte" group. >>> To unsubscribe from this group and stop receiving emails from it, send >>> an email to brain-mon-fte+unsubscribe(a)google.com. >>> To post to this group, send email to brain-mon-fte(a)google.com. >>> To view this discussion on the web visit https://groups.google.com/a/ >>> google.com/d/msgid/brain-mon-fte/CAMVr0Vy4KsyukWMA_7jfFzebONgVbD3Oh7wa% >>> 2Bk5eVxta8KYUVg%40mail.gmail.com. >>> >> >> >> -- >> Nicolas Le Roux >> >> _______________________________________________ >> Lisa_seminaires mailing list >> Lisa_seminaires(a)iro.umontreal.ca >> https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_seminaires >> >> > -- Nicolas Le Roux

1 0

[Tea Talk] Nicolas Le Roux (Google) May 25 2018 10:30 AM AA3195
by Michael Noukhovitch 25 Mai '18

25 Mai '18

This week we will have two tea talks (morning and afternoon) on Friday! Wow! The first talk will be *Nicolas Le* *Roux * on *May 25 2018* at *10:30 AM* in room *AA3195* (note the room change, we'll most likely be in 3195 for the summer). Streaming is, as always, at this link: https://bluejeans.com/809027115/webrtc but watch it live because there will be no recordings! Don't waver on going to this talk, it is sure to be invariantly excellent! Michael *TITLE* An exploration of variance reduction techniques in stochastic optimization *KEYWORDS *deep learning theory, optimization *ABSTRACT* I will present recent and ongoing work on reducing the variance in stochastic optimization techniques to speed-up and simplify the resulting algorithms. In particular, stochastic gradient methods can suffer from high variance, limiting their convergence speed. While variance reduction techniques exist in the finite case, they are rarer in the online case. We demonstrate how an increasing momentum offers variance reduction in the online case, at the expense of bias, and how that bias can be countered by an extrapolation step. The resulting algorithm differs from iterate averaging in only a factor, but, in the context of the minimization of a quadratic function, this difference is enough to lead to the first algorithm converging both linearly in the noiseless and sublinearly in the homoscedastic noise case when using a constant stepsize. *BIO* *Nicolas Le Roux got an MSc in Applied Maths from Ecole Centrale Paris and an MSc in Maths, Learning and Vision from ENS Cachan. He got his PhD in 2008 from University of Montreal where he worked with Yoshua Bengio on neural networks in general and their optimisation in particular. He then moved to Microsoft Research Cambridge to work on generative models of images with John Winn. In 2010, he joined Inria in Francis Bach's team to work on large-scale convex optimisation. From 2012 to 2017, he created and managed the research team at Criteo in Paris. He joined Google Brain Montreal in 2017 where he now works on large-scale optimization and reinforcement learning.*

2 4

No [Tea Talk] this week
by Michael Noukhovitch 14 Mai '18

14 Mai '18

Good luck to everyone rushing for NIPS! Michael

1 0

Re: [Lisa_teatalk] [Tea Talk] Martin Gilbert (IVADO) May 11 2018 10:30 AM AA1360
by Michael Noukhovitch 11 Mai '18

11 Mai '18

Reminder: talk is in 30 minutes On Mon, May 7, 2018, 14:14 Michael Noukhovitch <mnoukhov(a)gmail.com> wrote: > This week we have Martin Gilbert from IVADO giving a talk on May 11 2018 > at 10:30 AM in room AA1360 > > See you there! > Michael > > TITLE Intro to Ethics 2 > > KEYWORDS > > ABSTRACT > In this presentation, I will introduce to the three main families of > normative moral theories: consequentialism, deontologism and virtue ethics. > > BIO >

1 0

Re: [Lisa_teatalk] [Lisa_montreal] [Tea Talk] extra talk this afternoon 15:30, AA4488, on Ranking
by Yoshua Bengio 11 Mai '18

11 Mai '18

We have an extra tea-talk this afternoon at 15:30 in room AA4488: https://www.gerad.ca/fr/events/1589 A WEIGHTED CORRELATION INDEX FOR RANKINGS WITH TIESSebastiano Vigna <http://vigna.di.unimi.it/> – Università degli Studi di Milano, Italie Understanding the correlation between two different scores for the same set of items is a common problem in information retrieval, and the most commonly used statistics that quantifies this correlation is Kendall's tau. However, the standard definition fails to capture that discordances between items with high rank are more important than those between items with low rank. Recently, a new measure of correlation based on average precision has been proposed to solve this problem, but like many alternative proposals in the literature it assumes that there are no ties in the scores. This is a major deficiency in a number of contexts, and in particular while comparing centrality scores on large graphs, as the obvious baseline, in-degree, has a very large number of ties in web and social graphs. We propose to extend Kendall's definition in a natural way to take into account weights in the presence of ties. We prove a number of interesting mathematical properties of our generalization and describe an O(nlogn) algorithm for its computation. We also validate the usefulness of our weighted measure of correlation using experimental data. > _______________________________________________ > Lisa_montreal mailing list > Lisa_montreal(a)iro.umontreal.ca > https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_montreal > >

1 0

[Tea Talk] Martin Gilbert (IVADO) Fri May 11 2018 10:30 AM AA1360
by Michael Noukhovitch 07 Mai '18

07 Mai '18

This week we have our very own, Martin Gilbert from IVADO giving a follow-up on his previous Intro to Ethics talk on *Friday May 11 2018* at *10:30 AM* in room *AA1360* Come to this talk because you'll learn and improve your life, it's your duty as MILA students, and because going to tea talks would be very gracious of you! Michael *TITLE* Intro to Ethics 2 *ABSTRACT* In this presentation, I will introduce to the three main families of normative moral theories: consequentialism, deontologism and virtue ethics.

1 0

[Tea Talk] is cancelled for ICLR
by Michael Noukhovitch 02 Mai '18

02 Mai '18

No tea talk this week! Instead find someone to talk to about tea!

1 0

[Tea Talk] ICLR Lightning Talks! (MILA) Fri Apr 27 10:30AM AA1360
by Michael Noukhovitch 27 Avr '18

27 Avr '18

This week we have something special. *MILA students who have papers accepted at ICLR * will each be giving a 5-10 minutes talk on their work this *Friday Apr 27* at *10:30AM* in room *AA1360*. This should be fun and light, giving everyone a chance to see what your friends and colleagues have been up to, as well as congratulate them on their submissions! Make sure not to miss these electrifying talks! Michael Here's the list of papers being presented but there are even more (wow!) that made it into ICLR that aren't being presented *Fraternal Dropout* Konrad Zolna · Devansh Arpit · Dendi Suhubdy · Yoshua Bengio *Residual Connections Encourage Iterative Inference* Stanislaw Jastrzebski · Devansh Arpit · Nicolas Ballas · Vikas Verma · Tong Che · Yoshua Bengio *Deep Complex Networks* Chiheb Trabelsi · Olexa Bilaniuk · Ying Zhang · Dmitriy Serdyuk · Sandeep Subramanian · Joao Felipe Santos · Soroush Mehri · Negar Rostamzadeh · Yoshua Bengio · Christopher Pal *MaskGAN: Better Text Generation via Filling in the _______* William Fedus · Ian Goodfellow · Andrew Dai *Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step* William Fedus · Mihaela Rosca · Balaji Lakshminarayanan · Andrew Dai · Shakir Mohamed · Ian Goodfellow *Boundary Seeking GANs* R Devon Hjelm · Athul P Jacob · Adam Trischler · Tong Che · Kyunghyun Cho · Yoshua Bengio *Parametric Adversarial Divergences are Good Task Losses for Generative Modeling* Gabriel Huang · Hugo Berard · Ahmed Touati · Gauthier Gidel · Pascal Vincent · Simon Lacoste-Julien *Twin Networks: Matching the Future for Sequence Generation* Dmitriy Serdyuk · Nan Rosemary Ke · Alessandro Sordoni · Adam Trischler · Christopher Pal · Yoshua Bengio *ChatPainter: Improving Text to Image Generation using Dialogue* Shikhar Sharma · Dendi Suhubdy · Vincent Michalski · Samira Ebrahimi Kahou · Yoshua Bengio *FigureQA: An Annotated Figure Dataset for Visual Reasoning* Samira Ebrahimi Kahou · Vincent Michalski · Adam Atkinson · Ákos Kádár · Adam Trischler · Yoshua Bengio *Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning** Sandeep Subramanian · Adam Trischler · Yoshua Bengio · Christopher Pal *Learning Awareness Models** Brandon Amos · Laurent Dinh · Serkan Cabi · Thomas Rothörl · Sergio Gómez Colmenarejo · Alistair M Muldal · Tom Erez · Yuval Tassa · Nando d Freitas · Misha Denil *slides shown for presenters in absentia

1 1

[Extra Tea Talk] Masashi Sugiyama (RIKEN / U Tokyo) Thurs Apr 26 10:30AM AA3195
by Michael Noukhovitch 27 Avr '18

27 Avr '18

Next week we have an extra tea talk presented by *Masashi Sugiyama* from *RIKEN and University of Tokyo* giving a talk on *Thursday April 26* at *10:30AM* in room *AA3195* *note the different room* Want to meet Prof. Sugiyama? Sign up on the doodle <https://doodle.com/poll/b48c5gru3e89vpmc> We've only had great talks and I'm positive this one will be great too! Michael *TITLE* Machine learning from weak supervision - Towards accurate classification with low labeling costs. *KEYWORDS *semi-supervised learning, learning with biased data *ABSTRACT*Recent advances in machine learning with big labeled data allow us to achieve human-level performance in various tasks such as speech recognition, image understanding, and natural language translation. On the other hand, there are still many application domains where human labor is involved in the data acquisition process and thus the use of massive labeled data is prohibited. In this talk, I will introduce our recent advances in classification techniques from weak supervision, including classification from positive and unlabeled data, a novel approach to semi-supervised classification, classification from positive-confidence data, and classification from complementary labels *BIO* Masashi Sugiyama received the PhD degree in Computer Science from Tokyo Institute of Technology, Japan in 2001. He has been Professor at the University of Tokyo since 2014 and concurrently appointed as Director of RIKEN Center for Advanced Intelligence Project in 2016. His research interests include theory, algorithms, and applications of machine learning. He (co)-authored several books such as Density Ratio Estimation in Machine Learning (Cambridge University Press, 2012), Machine Learning in Non-Stationary Environments (MIT Press, 2012), Statistical Reinforcement Learning (Chapman and Hall, 2015), and Introduction to Statistical Machine Learning (Morgan Kaufmann, 2015). He served as a Program Co-chair and General Co-chair for the Neural Information Processing Systems conference in 2015 and 2016, respectively, and he will be a Program Co-chair for AISTATS2019. Masashi Sugiyama received the Japan Society for the Promotion of Science Award and the Japan Academy Medal in 2017.

2 2

Re: [Lisa_teatalk] [Extra Tea Talk] Masashi Sugiyama (RIKEN / U Tokyo) Thurs Apr 26 10:30AM AA3195
by Michael Noukhovitch 26 Avr '18

26 Avr '18

Reminder this is in 15 minutes! Steam is always here: https://bluejeans.com/809027115/webrtc On Thu, Apr 19, 2018, 10:53 Michael Noukhovitch <mnoukhov(a)gmail.com> wrote: > Next week we have an extra tea talk presented by *Masashi Sugiyama* from *RIKEN > and University of Tokyo* giving a talk on *Thursday April 26* at *10:30AM* > in room *AA3195* *note the different room* > > Want to meet Prof. Sugiyama? Sign up on the doodle > <https://doodle.com/poll/b48c5gru3e89vpmc> > > We've only had great talks and I'm positive this > Michael > > *TITLE* Machine learning from weak supervision - Towards accurate > classification with low labeling costs. > > *KEYWORDS *semi-supervised learning, learning with biased data > > > *ABSTRACT*Recent advances in machine learning with big labeled data allow > us to > achieve human-level performance in various tasks such as speech > recognition, image understanding, and natural language translation. On > the other hand, there are still many application domains where human > labor is involved in the data acquisition process and thus the use of > massive labeled data is prohibited. In this talk, I will introduce > our recent advances in classification techniques from weak > supervision, including classification from positive and unlabeled > data, a novel approach to semi-supervised classification, > classification from positive-confidence data, and classification from > complementary labels > > *BIO* > Masashi Sugiyama received the PhD degree in Computer Science from > Tokyo Institute of Technology, Japan in 2001. He has been Professor at > the University of Tokyo since 2014 and concurrently appointed as > Director of RIKEN Center for Advanced Intelligence Project in 2016. > His research interests include theory, algorithms, and applications of > machine learning. He (co)-authored several books such as Density Ratio > Estimation in Machine Learning (Cambridge University Press, 2012), > Machine Learning in Non-Stationary Environments (MIT Press, 2012), > Statistical Reinforcement Learning (Chapman and Hall, 2015), and > Introduction to Statistical Machine Learning (Morgan Kaufmann, 2015). > He served as a Program Co-chair and General Co-chair for the Neural > Information Processing Systems conference in 2015 and 2016, > respectively, and he will be a Program Co-chair for AISTATS2019. > Masashi Sugiyama received the Japan Society for the Promotion of > Science Award and the Japan Academy Medal in 2017. >

1 0

[Tea Talk] Ankit Anand (IIT Delhi) Fri Apr 20 10:30AM AA1360
by Michael Noukhovitch 20 Avr '18

20 Avr '18

This week we have *Ankit Anand* from *IIT Delhi* giving a talk on *Friday April 20* at *10:30AM* in room *AA1360*. ¡ʞlɐʇ ǝɥʇ oʇ ǝɯoɔ Michael *TITLE* Symmetry Aware Decision Making and Inference *KEYWORDS *AI Planning, Graphical Models, Image Segmentation/Stereovision *ABSTRACT* Many traditional AI algorithms fail to scale as the problem size increases exponentially with the number of features. This work focuses on using symmetries and abstractions to reduce computation and memory overhead in state-of-the-art AI and ML problems. Specifically, we exploit symmetries in sequential decision making under uncertainty (Monte Carlo Tree Search algorithms like UCT) and probabilistic inference. Abstractions and symmetries though well studied in the past have mostly been used as a preprocessing step. Our work focuses to learn symmetries and abstractions from scratch within the algorithm itself and use the learned abstractions and symmetries for further speeding up the state-of-the-art algorithms. Specifically, a) We propose ASAP-UCT and OGA-UCT which uses novel notion of Abstractions in Monte Carlo Tree Search Algorithms like UCT b) We apply symmetry aware graphical model inference in close to state-of-the-art Stereovision and Image Segmentation algorithms to gain impressive speed-ups without loss in quality c) We propose novel notion of symmetries -"Contextual Symmetries" and "Non-Count Symmetries" and use those for faster mixing in MCMC algorithms Moreover, our strategies are computationally efficient and provide gains up to 25% in International Probabilistic Planning Competition(IPPC) domains while speeding up MAP inference in Graphical Models by 10x for Stereovision and Segmentation without much loss in quality. *BIO* Ankit Anand <http://www.cse.iitd.ernet.in/~ankitanand/> is a PhD Student at Computer Science and Engineering department of IIT Delhi. He is advised by Dr. Parag Singla <http://www.cse.iitd.ac.in/~parags/> and Dr. Mausam <http://homes.cs.washington.edu/~mausam/>. His primary research interests are Artificial Intelligence Planning, Reinforcement Learning and Probabilistic Graphical Models. He has worked extensively on applications of Image Segmentation, Stereovision and Sequential Decision Making tasks. He is a recipient of Tata Consultancy Services Ph.D Fellowship from 2013-2016 and has published in top tier conferences like IJCAI, AAMAS, ICAPS and AISTATS. He is also a winner of best paper award at StarAI workshop at IJCAI'16.

2 3

[Tea Talk] Guillaume Lajoie (UdeM) Fri April 13 10:30AM AA1360
by Michael Noukhovitch 17 Avr '18

17 Avr '18

This week we have *Guillaume Lajoie* from *DMS *at *UdeM *giving a talk on *Friday April 13* at *10:30AM* in room *AA1360*. Make sure to come to this dynamic talk and your research will spike! Michael *TITLE *Dynamics of high-dimensional recurrent networks: how chaos shapes computation in biological and artificial neural networks *KEYWORDS *Dynamic Systems Analysis, Neuroscience, DL Theory *ABSTRACT*Networks of neurons —either biological or artificial— are called recurrent if their connections are distributed and contain feedback loops. Such networks can perform remarkably complex computations, as evidenced by their ubiquity throughout the brain and ever-increasing use in machine learning. They are, however, notoriously hard to control and their dynamics are generally poorly understood, especially in the presence of external forcing. This is because recurrent networks are typically chaotic systems, meaning they have rich and sensitive dynamics leading to variable responses to inputs. How does this chaos manifest in the neural code of the brain? How might we tame sensitivity to exploit complexity when training artificial recurrent networks for machine learning? Understanding how the dynamics of large driven networks shape their capacity to encode and process information presents a sizeable challenge. In this talk, I will discuss the use of Random Dynamical Systems Theory as a framework to study information processing in high-dimensional, signal-driven networks. I will present an overview of recent results linking chaotic attractors to entropy production, dimensionality and input discrimination of dynamical observables. I will outline insights this theory provides on how cortex performs complex computations using sparsely connected inhibitory and excitatory neurons, as well as implications for gradient-based optimization methods for artificial networks. *BIO*Since Jan 2018, Guillaume Lajoie is an Assistant Professor at the Math & Stats Dept. of UdeM. He obtained his PhD in applied mathematics from the University of Washington in 2013 and carried on research as an independent Bernstein Fellow at the Max Planck Institute for Dynamics and Self-Organization, as a visiting Scholar at the Courant Institute for Mathematical Sciences at NYU, and as a Washington Research Foundation Innovation Fellow at the University of Washington's Institute for Neuroengineering. His research interests lie at the intersection of applied mathematics, neuroscience and AI, where he works at leveraging tools from Dynamical Systems, Stochastic Processes, Information Theory and Machine Learning to better understand how recurrent network dynamics --either biological or artificial-- support computations. Applications of his research range from contributions to a theory of computation in recurrent networks, to the development of brain-computer interfaces.

2 2

[Tea Talk] Brady Neal (MILA) Fri Apr 4 10:30AM AA1360
by Michael Noukhovitch 06 Avr '18

06 Avr '18

This week we have our very own *Brady Neal* giving a talk this *Friday* at *10:30AM* in room *AA1360*. I may be a little bit biased, but coming to this talk will be at least one standard deviation better than your usual Friday! Michael *TITLE *Towards Understanding Generalization in Deep Learning by Revisiting the Bias-Variance Decomposition *KEYWORDS *DL Theory, ML Theory *ABSTRACT*Generalization is at the very core of machine learning. The bias-variance decomposition in machine learning is an underused lens to view generalization through. While it’s more common to derive upper bounds on the generalization gap via more complicated measures of complexity such as the VC dimension and Rademacher complexity, the bias-variance decomposition is an *equality* that is noticeably simpler. Looking through this lens, we can quickly get to partial explanations for why larger neural networks seem to generalize better than their smaller counterparts, despite the fact that bounds based on VC dimension and Rademacher complexity suggest the opposite. We appeal to some of the blessings of high dimensionality to do this. While Zhang et al. (2017) were quite surprised by the results of their experiments in “Understanding deep learning requires rethinking generalization,” they would have been much less surprised if they were looking at their results through the lens of the bias-variance decomposition. *BIO*Brady was an intern at MILA and is now a Masters student at MILA with Ioannis Mitliagkas. He organizes the DL Theory Reading Group and is currently focused on generalization and optimization in deep learning

2 3

No [Tea Talk] this Friday
by Michael Noukhovitch 27 Mar '18

27 Mar '18

For those of you who can't imagine how a Friday can be good without a research talk, I recommend watching this talk <https://www.youtube.com/watch?v=sT_-owjKIbA> on *How to Give a Great Research Talk* by Microsoft's *Simon Peyton Jones*. I think the talk is quite good and has some great ideas for when you all come to do your own tea talk (sign up for summer tea talks by emailing me!) Have a great Friday! Michael

1 0

[Tea Talk] Alex Ororbia (Penn State) Fri Mar 23 10:30AM AA1360
by Michael Noukhovitch 23 Mar '18

23 Mar '18

This week we have *Alexander G. Ororbia II* from *Penn State* giving a talk on *Friday March 23* at *10:30AM* in room *AA1360*. *Want to meet with Alex?* Fill out this Doodle <https://doodle.com/poll/6nkharwxw8ya26ys> and we'll find a spot! This talk should present some new ideas that will really challenge us to never stop learning, so you should definitely come! Michael *TITLE *Adaptation in the Face of Evolving Distributions: Towards Continual Learning of Connectionist Architectures *KEYWORDS *continual/lifelong/meta learning, optimization, biological-inspired RNN *ABSTRACT*It is a common statistical learning practice to build models on (very large) static datasets of identically and independently distributed samples. But what if the distribution to be learned is dynamic and samples are drawn from it over time? In this setting, these traditional learning approaches no longer directly apply. Motivated by this issue, we must look to continual, or lifelong learning, and the nature of systems that adapt themselves to such distributions. With the goal of creating robust and scalable continual learning systems, my work can be decomposed into two main threads: 1) creating architectures with longer-term memory and 2) developing better learning algorithms. In this talk, I will focus on the second thread, specifically on my efforts in developing alternatives to back-propagation of errors. Specifically, I will present, Local Representation Alignment (LRA), a training procedure that is much less sensitive to bad initializations, does not require modifications to the network architecture, can be readily adapted to networks with highly nonlinear and discrete-valued activation functions and stochastic sampling operations, and can even train networks with various kinds of activation functions from zero initialization. Results on classification benchmarks will be discussed and recent results in the lifelong learning setting, where the model must learn across tasks, will be presented. I will finally talk about my proposed neural architecture, the Temporal Neural Coding Network (TNCN), which builds on concepts from predictive coding, an important theory of the brain that has gained influence in cognitive science. Using the proposed Discrepancy Reduction learning procedure, which can be viewed as a special variation of LRA, the TNCN can learn from sequential data, such as videos or text documents. More importantly, initial results show promise that the TNCN can be competitive with models that learn using back-propagation through time--the popular, biologically implausible algorithm used to "unroll" and train recurrent neural networks. *BIO* Alex is currently a Ph.D. student at The Pennsylvania State University in Information Sciences & Technology. In 2013, he obtained his Bachelor of Science degree in Computer Science & Engineering at Bucknell University, minoring in Philosophy and Mathematics. The focus of his work is on lifelong learning--an important and challenging open problem in machine learning. He studies representation learning and draws inspiration from ideas in cognitive science and neuroscience. Alex's mission is to develop the learning procedures and architectures needed to create general-purpose, adaptive agents that can learn from data of multiple modalities and operate in messy, non-stationary environments.

1 1

[Special Seminar] François Laviolette (ULaval) Mon Mar 26 3pm PCM Z240
by Michael Noukhovitch 21 Mar '18

21 Mar '18

Early next week we will have *François Laviolette* from *Université Laval* giving a talk on *Monday March 26* at *3pm* in room *Claire-McNicoll (CM) Z240*. *Want to meet with Prof. Lavoilette?* Fill out this Doodle <https://doodle.com/poll/yan2dz5fsgsvm9cs> Learn how to improve the lower bound on your knowledge! Michael *TITLE *PAC-Bayesian Analysis and Its Applications *KEYWORDS* ML Theory, Statistics, DL Theoretic Bounds *ABSTRACT*PAC-Bayesian analysis is a basic and very general tool for data-dependent analysis of the generalization performance of learning algorithms. By now, it has been applied in diverse areas, such as supervised learning, unsupervised learning, and reinforcement learning, leading to state-of-the-art algorithms and generalization bounds. PAC-Bayesian analysis, in a sense, takes the best out of Bayesian methods and the more frequentist approach related to PAC learning and puts it together: (1) it provides an easy way to exploit prior knowledge (like Bayesian methods); (2) it provides strict and explicit generalization guarantees (like VC theory); and (3) it is data-dependent and provides an easy and strict way of exploiting benign conditions (like Rademacher complexities). In addition, PAC-Bayesian bounds directly lead to efficient learning algorithms. We will start with a general introduction to PAC-Bayesian analysis, which should be accessible to people with prior knowledge of machine learning. Then, we will survey multiple forms of PAC-Bayesian bounds and their numerous applications in different fields (including deep learning). Some of these applications will be explained in more details, while others will be surveyed at a high level. *BIO* Professor François Laviolette is the founding director of the Big Data Research Centre (BDRC) of Université Laval, which regroups more than 47 researchers from five faculties working on different fundamental and applied aspects of data science. He has been a full professor in the Department of Computer Science and Software Engineering of Université Laval since 2002. Prof. Laviolette's main research involves Machine Learning and Big Data Analytics. He is a world-class leader in PAC-Bayesian theory, a branch of learning theory that gives rise to a better understanding of existing machine learning algorithms, and also makes it possible to design new ones. Professor Laviolette has also developed a strong expertise in bio-informatics. In that area, he worked on interpretable machine learning algorithms that were able to uncover valuable knowledge for new medical applications. Professor Laviolette is the lead researcher of the GRAAL laboratory of Laval University, whose mission is to conduct research on Machine Learning fundamentals and to develop innovative artificial intelligence applications. Over the past six years, Prof. Laviolette has supervised and co-supervised more than 36 graduate students members of the GRAAL.

1 0

[Tea Talk] Alexander Vezhnevets (Deepmind) Fri Mar 16 10:30AM AA1360
by Michael Noukhovitch 16 Mar '18

16 Mar '18

This week we are lucky to have *Alexander Vezhnevets*, research scientist at *Deepmind,* giving a talk on *Friday March 16* at *10:30AM* in room *AA1360*. If you want to meet with Alexander in the afternoon, add your name and the times you're free here: https://doodle.com/poll/6bbzqikmtx5nuktv Navigate your way, by walking and taking the elevator, specfically moving towards the elevator, taking the elevator down, exit the elevator, and making your way to room 1360 to come to this funtastic talk! Michael *TITLE *What we want from (H)RL and other FuN topics *KEYWORDS *Hierarchical Learning, RL, Compositional Learning *ABSTRACT*Deep Reinforcement learning is making headlines. Superhuman at Go and Space Invaders, possibly Starcraft next! Yet most of the state of the art, human beating architectures are reactive and data hungry. They don’t possess transferable skills, can’t break complex tasks into sub-task, plan into the future or find more than one solution to a problem. Hierarchical reinforcement learning is an area of research that aims to build agents with complex, structured behaviour by endowing them with all of these desired properties of intelligence. In this talk we will review the recent progress in HRL and discuss one model - FeUdal Networks - in more details. FeUdal Networks (FuN) is a neural network architecture, which learns to decompose its behaviour into meaningful primitives and then reuse them to more efficiently acquire new, complex behaviours. This allows it to reason on different temporal resolutions and thereby improve long-term credit assignment and memory. *BIO*Alexander Vezhnevets is a research scientist at DeepMind working on hierarchical RL. Originally from Moscow, he got his PhD in Machine Learning from ETH Zurich, where he worked with Joachim Buhmann on structured output learning. He then spent two years in lovely Edinburgh working on computer vision with Vittorio Ferrari.

1 1

[Tea Talk] Martin Gilbert (IVADO) Fri Mar 9 10:30AM AA1360
by Michael Noukhovitch 09 Mar '18

09 Mar '18

This week we have* Martin Gilbert *from *IVADO* giving a talk on *Friday March 9th* at *10:30AM* in room *AA1360*. You wouldn't download a car on your way to the talk? Would you? Michael *TITLE* An introduction to ethics for computer scientists *KEYWORDS *Ethics, Philosophy *ABSTRACT*In this general introduction to ethics, basic concepts and theories used by contemporary ethicist will be presented: the 3 parts of ethics, normative vs descriptive judgments, prudential vs ethical judgments, the 3 normative theories (about values, norms and virtues), moral minimalism vs maximalism. *BIO* Martin Gibert is researcher in ethics of AI à University of Montreal (IVADO, CRÉ) and coordinator of the Montreal declaration for a responsible AI. He has published L'imagination en morale (Hermann, 2014) and Voir son steak comme un animal mort (Lux, 2015).

2 2

[DIRO Talk] Devon Hjelm (MILA) Fri Mar 2 10:30AM AA1360
by Michael Noukhovitch 02 Mar '18

02 Mar '18

For our last special DIRO talk, we have our very own *Devon Hjelm* giving a talk on *Friday March 2* at *10:30AM* in room *AA1360*. This talk has generated a lot of interest, so come take a GANder and judge for yourself if it's the real deal! Michael *TITLE *Research in Generative Adversarial Learning *KEYWORDS* Unsupervised learning, generative models, representation learning, adversarial learning, mutual information *ABSTRACT* Since their inception, generative adversarial networks (GANs) have emerged as a state-of-the-art approach for generating high-dimensional continuous data. As the field has grown, so has its applications, with the underlying principles of GANs having been extended into numerous problems in unsupervised learning. This talk will cover the basic principles of GANs, as well as briefly summarize our three recent works that cover different types of unsupervised problems using these principles: 1) Discrete generation in GANs (Boundary seeking GANs, ICLR 2018): Training GANs with discrete data (e.g., natural language as realized as a sequence of character or word tokens) is normally not possible due to being unable to backprop. We introduce a principled approach for training GANs with discrete data that draws from likelihood ratio estimation, importance sampling, and policy gradients. 2) Learning richer representations in bidirectional adversarial models (GibbsNet, NIPS 2017). Undirected graphical models (e.g., RBMs, DBMs) can provide richer representations than those available from directed graphical models (e.g., VAEs). We draw from ideas in undirected graphical models to formulate an adversarial model that learns a representation that is richer than competing adversarial models. 3) Neural mutual information estimation (MINE, in review): Mutual information is notoriously difficult to compute, especially in the high-dimensional continuous setting. We introduce a general-purpose neural estimator for mutual information which is scalable, flexible, and completely trainable via back-prop. *BIO* R Devon Hjelm earned his PhD at the University of New Mexico under the supervision of Vince Calhoun at the Mind Research Network, a research institute dedicated to neuro-diagnostic discovery. Prior to this, he acquired a Master’s degree in Physics (with a focus on Quantum Information) and Linguistics. He joined the Montréal Institute for Learning Algorithms (MILA) at the University of Montréal in January 2017 as an IVADO “distinguished researcher” postdoctoral fellow under Yoshua Bengio. There, his research focus became adversarial learning (GANs), notably applying ideas from GANs to solving a broader class of unsupervised learning problems. Ultimately, he is primarily interested in research on training an agent that is able to reason about the natural world from evidence and communicate its understanding to humans. *PHOTO* *(real sample, not generated)* *[image: CD2F92BF-5584-473C-BE37-5D616C37B293.png]*

1 1