Lisa_seminaires

lisa_seminaires@iro.umontreal.ca

396 discussions

Fwd: J'organise ce séminaire au GERAD, mercredi 7 déc., 15h45
by Yoshua Bengio 05 Déc '16

05 Déc '16

---------- Message transféré ---------- De : *Pierre Lecuyer* <lecuyer(a)iro.umontreal.ca> Date : lundi 5 décembre 2016 Objet : J'organise ce séminaire au GERAD, mercredi 7 déc., 15h45 À : seminaires <seminaires(a)iro.umontreal.ca>, "Manuel Morales (UdeM)" < morales(a)dms.umontreal.ca>, Christian Leger <leger(a)dms.umontreal.ca>, francois.bellavance(a)hec.ca, cgenest(a)math.mcgill.ca, MACGIBBON BRENDA < macgibbon.brenda(a)uqam.ca>, bruno.remillard(a)hec.ca, Francois Perron < perronf(a)crm.umontreal.ca>, bedard(a)dms.umontreal.ca, hatem ben-ameur < hatem.ben-ameur(a)hec.ca>, cotemyri(a)iro.umontreal.ca, Zdravko Botev < botev(a)unsw.edu.au> SVP diffuser aux intéressés. Détails ici: https://www.gerad.ca/fr/events/1407 Novel computational approaches to the Bayesian and frequentist lasso regression Zdravko I. Botev <http://web.maths.unsw.edu.au/%7Ezdravkobotev/> – The University of New South Wales, Australie The Lasso regression model is one of the simplest and most popular penalized regression models in statistics. In this talk we describe a simple Monte Carlo method for sampling from the posterior density of the Bayesian posterior of the Lasso. We show how the construction of such an efficient Monte Carlo sampler necessitates that we solve the frequentist Lasso optimization problem in a novel way. We give a numerical example with the well-known diabetes dataset of Efron. This is joint work with Pierre L'Ecuyer. ------------------------------ -- Pierre L'Ecuyer, Professeur Titulaire Chaire du Canada en Simulation et Optimisation Stochastique CIRRELT, GERAD, and DIRO, Université de Montréal, Canadahttp://www.iro.umontreal.ca/~lecuyer

1 0

You're invited to Let's celebrate our growing AI community & Jeremy... (Dec 2, 2016)
by Francis Pieraut 01 Déc '16

01 Déc '16

A french version will follow.  DISCOUNT 50% for MILA NETWORK We beleive 2016 will stay as historical date for AI in the world and it is happening in MTL. Many of the world leaders are from MTL and we should consider us lucky. As an example Yoshua, one of the father of the Deeplearning revolution is a  Full professor at Université de Montréal.  Let's take a moment to acknoledge some of the milestone of our community to end the year well and celebrate by the same time Jeremy Barnes, CEO mldb.ai, major contribution to our eco-system.  We are happy to welcome you in the #DesjardinsLab for a fast summary of our achievements as a growing comminity and to celebrate Jeremy 40 years old birthday as it should be. Its a community initiative, ticket price will found drinks and food. A special thanks to Desjardins to welcome us in their Lab and MTLNewTech to have supported us in this initiative. Don't hesitate to to share the invitation, we wish to take the opportunity to bring togetter the actors of the MTL AI community, we should do it more. As mentioned by usingularity, tech will help humanity moving from scacity to aboundance management. MTL, as the capital of AI, intent to due is duty and will help disrupting some industries such as Fintech, IOT, Retail, Healtcare etc. We have a phenomenal ecosystem and should be self-aware of it and say it loud: Leadership in Deeplearning, Optimisation, Big-Data etc. 6 university + education is accessible here not like in the US + great pool of talent VC (inovia, realventure etc.) Entrepreneur training (founder fuel, Founder Institute, tandemlauch, International startup weekend, FCP Fintech etc.) Great government support (SRED, NRC, crsng etc.) Entrepreneur network (EO, EA, FounderDating, MTL startup Cabal, startup openhouse etc.) Let's continue connecting the dots in order to make sure Silicon Valley will surender to MTL dominance in AI.   VERSION FRANCAISE Nous sommes persuadé que l'année 2016 va rester comme une année marquante de l'histoire de l'AI dans le monde, et c'est à Montréal que ça se passe! Nous avons tellement d'acteurs qui y contribuent tous les jours, et avons la chance d'avoir de nombreux pionniers de cette révolution à Montréal tel que l'un des 3 piliers de la révolution du deeplearning Yoshua Bengio!  Prenons un moment revenir sur les milestones que notre communauté a parcouru, et clore l'année en beauté, avant un 2017 qui sera encore plus excitant! Et quelle meilleure manière de le faire que de profiter du 40ème anniversaire de Jeremy qui a fondé MLDB.ai qui est un des précurseur de cet écosystème (demo)!  On vous invite donc au #DesjardinsLAB pour un rapide retour sur nos avancées en tant que communauté, et célébrer l'annivesaire de Jeremy comme il se doit! C'est une initiative communautaire, le prix des billets servira à offrir boissons et bouchées. Gros merci à Desjardins LAB pour l'accueil et MTL NewTech pour le support par ailleurs ;) N'hésitez pas à partager l'invitation, nous voulons vraiment saisir cette opportunité pour rassembler les acteurs de la communauté AI de Montréal pour célébrer ensemble! (on le fait pas assez!!! ;) ) Tel que mentioné par les leaders de usingularity.org, la technologie va nous aider à passer d'un modèle de "scarcity" à la gestion de l'abondance. Montréal, en tant que capitale de l'intelligence artificielle, compte aider l'umanité à utiliser l'intelligence artificielle pour perturber les domaines suivant: Fintech, IOT, Retail, healthcare etc. Nous avons un écosystème phénoménale et nous devons en être conscient et le dire haut et fort: Leadership in Deeplearning, Optimisation, Big-Data etc.  6 university + education is accessible here not like in the US + great pool of talent VC (inovia, realventure etc.) Entrepreneur training (founder fuel, Founder Institute, tandemlauch, International startup weekend, FCP Fintech etc.) Great government support (SRED, NRC, crsng etc.) Entrepreneur network (EO, EA, FounderDating, MTL startup Cabal, startup openhouse etc.)  Let continue connecting the dot in order to make sure Silicon Valley will surender to MTL dominance in AI.  Merci, -- Francis Piéraut, eng., M.A.Sc. Intrapreneur/Community builder/Machine Learning Geek, co-organizer Big-Data-MTL usergroup + Connector/enabler SiliconIsland/MTLvalley 1-514-464-3562 tech blog: http://fraka6.blogspot.ca/ Share this event on Facebook and Twitter We hope you can make it!Cheers,Francis Pieraut ------------------------------ Event Summary: ------------------------------ Event: Let's celebrate our growing AI community & Jeremy contributions Date: Friday, December 2, 2016 from 6:00 PM to 10:00 PM (EST) Location: Desjardins LAB 175 René Levesque Ouest Rez-de-chaussé - Espace Desjardins Montreal, Quebec H2X 3Y2 Canada ------------------------------ Event Details: ------------------------------ An english version will follow. Nous sommes persuadé que l'année 2016 va rester comme une année marquante de l'histoire de l'AI dans le monde, et c'est à Montréal que ça se passe! Nous avons tellement d'acteurs qui y contribuent tous les jours, et avons la chance d'avoir de nombreux pionniers de cette révolution à Montréal tel que l'un des 3 piliers de la révolution du deeplearning Yoshua Bengio! Prenons un moment revenir sur les milestones que notre communauté a parcouru, et clore l'année en beauté, avant un 2017 qui sera encore plus excitant! Et quelle meilleure manière de le faire que de profiter du 40ème anniversaire de Jeremy qui a fondé MLDB.ai qui est un des précurseur de cet écosystème (demo)! On vous invite donc au #DesjardinsLAB pour un rapide retour sur nos avancées en tant que communauté, et célébrer l'annivesaire de Jeremy comme il se doit! C'est une initiative communautaire, le prix des billets servira à offrir boissons et bouchées. Gros merci à Desjardins LAB pour l'accueil et MTL NewTech pour le support par ailleurs ;) N'hésitez pas à partager l'invitation, nous voulons vraiment saisir cette opportunité pour rassembler les acteurs de la communauté AI de Montréal pour célébrer ensemble! (on le fait pas assez!!! ;) ) Tel que mentioné par les leaders de usingularity.org, la technologie va nous aider à passer d'un modèle de "scarcity" à la gestion de l'abondance. Montréal, en tant que capitale de l'intelligence artificielle, compte aider l'umanité à utiliser l'intelligence artificielle pour perturber les domaines suivant: Fintech, IOT, Retail, healthcare etc. Nous avons un écosystème phénoménale et nous devons en être conscient et le dire haut et fort: Leadership in Deeplearning, Optimisation, Big-Data etc. 6 university + education is accessible here not like in the US + great pool of talent VC (inovia, realventure etc.) Entrepreneur training (founder fuel, Founder Institute, tandemlauch, International startup weekend, FCP Fintech etc.) Great government support (SRED, NRC, crsng etc.) Entrepreneur network (EO, EA, FounderDating, MTL startup Cabal, startup openhouse etc.) Let continue connecting the dot in order to make sure Silicon Valley will surender to MTL dominance in AI. English summart version: We beleive 2016 will stay as historical date for AI in the world and it is happening in MTL. Many of the world leaders are from MTL and we should consider us lucky. As an example Yoshua, one of the father of the Deeplearning revolution is a Full professor at Université de Montréal. Let's take a moment to acknoledge some of the milestone of our community to end the year well and celebrate by the same time Jeremy Barnes, CEO mldb.ai, major contribution to our eco-system. We are happy to welcome you in the #DesjardinsLab for a fast summary of our achievements as a growing comminity and to celebrate Jeremy 40 years old birthday as it should be. Its a community initiative, ticket price will found drinks and food. A special thanks to Desjardins to welcome us in their Lab and MTLNewTech to have supported us in this initiative. Don't hesitate to to share the invitation, we wish to take the opportunity to bring togetter the actors of the MTL AI community, we should do it more. As mentioned by usingularity, tech will help humanity moving from scacity to aboundance management. MTL, as the capital of AI, intent to due is duty and will help disrupting some industries such as Fintech, IOT, Retail, Healtcare etc. We have a phenomenal ecosystem and should be self-aware of it and say it loud: Leadership in Deeplearning, Optimisation, Big-Data etc. 6 university + education is accessible here not like in the US + great pool of talent VC (inovia, realventure etc.) Entrepreneur training (founder fuel, Founder Institute, tandemlauch, International startup weekend, FCP Fintech etc.) Great government support (SRED, NRC, crsng etc.) Entrepreneur network (EO, EA, FounderDating, MTL startup Cabal, startup openhouse etc.) Let's continue connecting the dots in order to make sure Silicon Valley will surender to MTL dominance in AI. Merci, -- Francis Piéraut, eng., M.A.Sc. Intrapreneur/Community builder/Machine Learning Geek, co-organizer Big-Data-MTL usergroup + Connector/enabler SiliconIsland/MTLvalley 1-514-464-3562 tech blog: http://fraka6.blogspot.ca/ ------------------------------ Hosted By: ------------------------------ Francis Pieraut Francis hate/love Montreal and has decided to build instead of leaving this mediocre city because he won't leave his kids here. Francis disupt all win/loose models and connect the dots to make MTL reach faster its destiny: The SiliconIsland of AI proudly made in MTL. ------------------------------ Register Online: ------------------------------ More information and online registration are available here: https://www.eventbrite.com/e/lets-celebrate-our-growing-ai-community-jeremy… ---------------------------------------------------------------------- Collect event fees online with Eventbrite http://www.eventbrite.com

1 0

Fwd: Séminaire machine learning par Prof Melko
by Yoshua Bengio 30 Nov '16

30 Nov '16

Interesting upcoming talk, Dec. 12, on machine learning for astronomy. ---------- Message transféré ---------- De : Witczak-Krempa William <w.witczak-krempa(a)umontreal.ca> Date : 30 novembre 2016 à 13:49 Objet : Séminaire machine learning par Prof Melko À : "bengioy(a)iro.umontreal.ca" <bengioy(a)iro.umontreal.ca>, Bengio Yoshua < yoshua.bengio(a)umontreal.ca> Cc : Lewis Laurent J <laurent.lewis(a)umontreal.ca> Bonjour Yoshua, CC Laurent Lewis, Il y aura un séminaire donné par Roger Melko (U. of Waterloo) intitulé "Machine Learning the Many-Body Problem” le 12 décembre à 11:30am: http://www.calendrier.umontreal.ca/detail/717846-machine-learning-the-many- body-problem-roger-melko-u-of-waterloo Je me demandais si serais possible de diffuser l’information au près des gens en informatique qui seraient potentiellement intéressés? Merci! Cordialement, William —— Professeur Adjoint | Assistant Professor Canada Research Chair Université de Montréal Pavillion Roger-Gaudry, 2900 boul. Édouard-Montpetit Bureau | office: A-405 T: 514-343-6669 W: http://physique.umontreal.ca/wwk

1 0

[Talk] Prof. Wulfram Gerstner on "Synaptic Plasticity to Learning Rules: an approach of theoretical neuroscience"
by Junyoung Chung 23 Nov '16

23 Nov '16

Hi everyone, on next Tuesday, we will have a guest tutorial on neuroscience by professor Wulfram Gerstner who is visiting our lab for two weeks. Looking forward to see many of you there! Who: Wulfram Gerstner When: Nov. 22 (Tuesday) 3PM-5PM Where: AA6214 Title: Synaptic Plasticity to Learning Rules: an approach of theoretical neuroscience Abstract: In this tutorial I will show what type of constraints experimental data set for biologically plausible learning rules and why inside these constraints we (as theoretical neuroscientists) have a lot of freedom to think about learning rules that are functionally relevant in learning paradigms. Taking examples from unsupervised learning, reinforcement learning, and surprise modulated learning I will point out potential links (and differences) to machine learning approaches. Bio: Wulfram Gerstner is Director of the Laboratory of Computational Neuroscience LCN at the EPFL. He studied physics at the universities of Tubingen and Munich and received a PhD from the Technical University of Munich. His research in computational neuroscience concentrates on models of spiking neurons and spike-timing dependent plasticity, on the problem of neuronal coding in single neurons and populations, as well as on the role of spatial representation for navigation of rat-like autonomous agents. He currently has a joint appointment at the School of Life Sciences and the School of Computer and Communications Sciences at the EPFL. He teaches courses for Physicists, Computer Scientists, Mathematicians, and Life Scientists. Best, --Junyoung

4 5

Dialogue-based learning talk by Jason Weston
by Tegan Maharaj 17 Nov '16

17 Nov '16

Hi everyone, The tea talk this week will be Jason Weston's talk about dialogue. Who: Jason Weston When: Nov. 17 (Today) 3:00PM Where: PAA 1207 Title: Dialog-based Language Learning Abstract: We study how to learn to use language via dialog-based language learning, where supervision is given naturally and implicitly in the response of the dialog partner during the conversation. Experiments are in two domains: the bAbI dataset of (Weston et al., 2015) and the larger movieQA dataset from (Dodge et al., 2015). We evaluate a set of baseline learning strategies on these tasks, and show that a novel model incorporating predictive lookahead is a promising approach for learning from a teacher's response. In particular, a surprising result is that it can learn to answer questions correctly without any reward-based supervision at all. This is joint work with Jiwei Li, Alex Miller, Sumit Chopra and Marc'Aurelio Ranzato Hope to see you there! Cheers, Tegan

1 0

Fwd: [Stats] McGill Statistics Seminar Series - THIS FRIDAY
by Yoshua Bengio 16 Nov '16

16 Nov '16

---------- Forwarded message ---------- From: Yi Yang <yi.yang6(a)mcgill.ca> Date: 2016-11-15 11:14 GMT-05:00 Subject: [Stats] McGill Statistics Seminar Series - THIS FRIDAY To: stats.students(a)math.mcgill.ca, stats(a)math.mcgill.ca, EBOH Secretary < secretary.eboh(a)mcgill.ca>, "Jackie Castreje, Ms." <jackie.castreje(a)mcgill.ca>, Yoshua Bengio <yoshua.umontreal(a)gmail.com> *McGill Statistics Seminar Series* Friday, *November 18* 2016, 15:30 – 16:30 Room 1205, Burnside Hall, 805 Sherbrooke West ______________________________________________________ * Progress in Theoretical Understanding of Deep Learning* Yoshua Bengio, PhD Professor, University of Montreal Deep learning has arisen around 2006 as a renewal of neural networks research allowing such models to have more layers. Theoretical investigations have shown that functions obtained as deep compositions of simpler functions (which includes both deep and recurrent nets) can express highly varying functions (with many ups and downs and different input regions that can be distinguished) much more efficiently (with fewer parameters) than otherwise, under a prior which seems to work well for artificial intelligence tasks. Empirical work in a variety of applications has demonstrated that, when well trained, such deep architectures can be highly successful, remarkably breaking through previous state-of-the-art in many areas, including speech recognition, object recognition, language models, machine translation and transfer learning. Although neural networks have long been considered lacking in theory and much remains to be done, theoretical advances have been made and will be discussed, to support distributed representations, depth of representation, the non-convexity of the training objective, and the probabilistic interpretation of learning algorithms (especially of the auto-encoder type, which were lacking one). The talk will focus on the intuitions behind these theoretical results. Organized by the McGill Statistics Group. Seminar website: http://www.math.mcgill.ca/node/5358 -- Yi Yang Assistant Professor of Statistics Department of Mathematics and Statistics McGill University http://www.math.mcgill.ca/yyang/

1 0

Fwd: C'est celui-là, Yoshua,
by Yoshua Bengio 29 Oct '16

29 Oct '16

Please all come to this talk (in English) Wednesday 3:30pm @ 6214, by Augustin Chaintreau from Columbia. -------- Forwarded Message -------- Subject: colloque DIRO *mercredi* 2 nov, Augustin Chaintreau (Columbia) Date: Sat, 29 Oct 2016 11:32:53 -0400 From: Pierre McKenzie <mckenzie(a)iro.umontreal.ca> <mckenzie(a)iro.umontreal.ca> To: seminaires(a)iro.umontreal.ca *Fixing our Opaque, Fragmented and Disparate Big Data* par *Augustin Chaintreau * Columbia University *Mercredi 2 novembre, 15:30-16:30*, *Salle 6214*, Pavillon André-Aisenstadt Université de Montréal, 2920 Chemin de la Tour The conference will be held in English. *ATTENTION: *horaire et salle inhabituels pour un colloque du DIRO. *Résumé * Today's big data is flawed, and the threats it poses are not theoretical: We show with reproducible experiments that personalization algorithms in services used by millions pose moral hazards, that metrics of social endorsement are vastly misleading, and that the network dynamics facilitated by online interactions and sharing economies stand in the way of reducing various inequalities. Personal information collection and usage, however, ultimately bring benefits that we cannot forego, including in areas such as health, energy efficiency and public policies. Opacity, Fragmented Views, and Disparate Impact may appear embedded in the fabric of Big Data; we show, on the contrary, from multiple examples that these trends can be reversed. Our first challenge is transparency and accountability in today's personalization, for which we provide a scalable solution validated on three leading services. We then address how to leverage opportunities offered by personal data in different domains, while informing mobile consumers and social media participants on their risks. Finally, we model how parsimonious individuals disparately benefit from information shared locally on a social network. Our analysis reveals general conditions on a network spectral expansion to eventually benefit all its members, closely related to the presence to special segregations between groups of users. *Biographie* Augustin is an Assistant Professor of Computer Science at Columbia University since 2010, where he directs the Mobile Social Lab. The goal of his research is to reconcile the benefits of leveraging personal data and social networks with a commitment to fairness and privacy. His latest results address transparency in personalization, the role of human mobility in privacy across several domains, the efficiency of crowdsourced content curation, the fairness of incentives to share personal data. His research lead to 25 papers in tier-1 conferences (five receiving best or best student paper awards at ACM CoNEXT, SIGMETRICS, USENIX IMC, IEEE MASS, Algotel), covered by several media including the NYT blog, The Washington Post, the Economist, or The Guardian. An ex student of the Ecole Normale Supérieure in Paris, he earned a Ph.D in mathematics and computer science in 2006, a NSF CAREER Award in 2013 and the ACM SIGMETRICS Rising star award in 2013. He has been an active member of network and web research community, organizing the upcoming Data Transparency Lab Conference, serving in the program committees of ACM SIGMETRICS (as chair), SIGCOMM, WWW, CoNEXT (as chair), MobiCom, MobiHoc, IMC, WSDM, WWW, COSN, AAAI ICWSM, and IEEE Infocom, and as area editor for IEEE TMC, ACM SIGCOMM CCR, and ACM SIGMOBILE MC2R.

1 0

[TeaTalk] Geordie Rose on "Building a system for embodied intelligence research"
by Junyoung Chung 27 Oct '16

27 Oct '16

Hi everyone, this Friday, we will have a teatalk by Geordie Rose who has co-founded D-Wave and Kindred. Looking forward to see many of you there! Who: Geordie Rose When: Oct. 28th (Friday) 11AM Where: AA6214 Title: Building a system for embodied intelligence research Abstract: Animals, including humans, have intelligence that is embodied -- it resides within a body. Brains evolved to control these bodies, and human intelligence seems to be a side effect of this process. I would like to explore in an interactive way with the audience what characteristics a research system would have that would allow exploration of how embodied intelligence works. This research system would include robots, control systems, programming interfaces, tele-operation, and potentially other useful characteristics. Bio: Geordie Rose is co-founder and CEO of Kindred (www.kindred.ai), and was the founder of D-Wave (for more details visit gr.ai). --Junyoung

1 1

Yann Lecun
by linda p 21 Sep '16

21 Sep '16

Hi all, I would like to remind that Yann Lecun's confenrence will be held today at 15h15, room S1-151, pavillon Jean-Coutu and it will be in *english*. You're all welcome Linda Peinthière Technicienne en coordination de bureau MILA 514-343-6111 ext. 1868

1 0

Fwd: 21 septembre: journée remplie d'IA au DIRO
by Yoshua Bengio 17 Sep '16

17 Sep '16

---------- Message transféré ---------- De : Guy Lapalme <lapalme(a)iro.umontreal.ca> Date : 17 septembre 2016 à 08:56 Objet : 21 septembre: journée remplie d'IA au DIRO À : rali-olst(a)iro.umontreal.ca À tous les auditeurs de la liste RALI-OLST mercredi prochain, en plus de notre séminaire habituel à 11h30 pour lequel vous avez déjà reçu l'annonce ** Some recent research on Chinese-English Patent Machine Translation Hongzheng (Victor) Li Il y aura deux autres présentations reliées à l'IA ** L'apprentissage prédictif et le futur de l'intelligence artificielle Yann LeCun (Facebook AI Research et New York University) 15 h 15, Salle S1-151 du pavillon Jean-Coutu plus de détails à http://diro.umontreal.ca/departement/conferenciers-emerites/ ** La révolution de l’intelligence artificielle par Yoshua Bengio, Yann LeCun et Joelle Pineau (U. McGill) 18h, Amphithéâtre Ernest-Cormier (K-500) du Pavillon Roger-Gaudry Plus de détails à: http://cdlm.umontreal.ca --- Bienvenue à tous Guy Lapalme

1 0

Aller à la page :

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

Lisa_seminaires