Lisa_seminaires Juillet 2017

lisa_seminaires@iro.umontreal.ca

4 participants
5 discussions

[TeaTalk] James Wright, July 28, AA6214, 13:45
by Dzmitry Bahdanau 28 Jul '17

28 Jul '17

Hi all, Our next speaker is James Wright from Microsoft Research NYC. The talk will take place on July 28, at AA6214, 13:45. Hope to see many of there! Title: Deep Learning for Predicting Human Strategic Behavior Abstract: Predicting the behavior of human participants in strategic settings is an important problem in many domains. Most existing work either assumes that participants are perfectly rational, or attempts to directly model each participant's cognitive processes based on insights from cognitive psychology and experimental economics. In this work, we present an alternative, a deep learning approach that automatically performs cognitive modeling without relying on such expert knowledge. We introduce a novel architecture that allows a single network to generalize across different input and output dimensions by using matrix units rather than scalar units, and show that its performance significantly outperforms that of the previous state of the art, which relies on expert-constructed features. Bio: James Wright's research focuses on problems at the intersection of economics, behavioral modeling, and machine learning, with a focus on modeling and predicting human behavior in strategic settings. Prior to joining Microsoft Research NYC, he completed a Ph.D. in Computer Science at the University of British Columbia, where he was advised by Kevin Leyton-Brown. Dima

1 2

Eugene Vorontsov, July 21, AA6214, 13:45
by Junyoung Chung 21 Jul '17

21 Jul '17

Hi all, our next speaker is Eugene Vorontsov. Hope to see you many of you there. When: 13:45, July 21 Where: AA6214 Title: On orthogonality and learning recurrent networks with long term dependencies Abstract: It is well known that it is challenging to train deep neural networks and recurrent neural networks for tasks that exhibit long term dependencies. The vanishing or exploding gradient problem is a well known issue associated with these challenges. One approach to addressing vanishing and exploding gradients is to use either soft or hard constraints on weight matrices so as to encourage or enforce orthogonality. Orthogonal matrices preserve gradient norm during backpropagation and may therefore be a desirable property. This paper explores issues with optimization convergence, speed and gradient stability when encouraging or enforcing orthogonality. To perform this analysis, we propose a weight matrix factorization and parameterization strategy through which we can bound matrix norms and therein control the degree of expansivity induced during backpropagation. We find that hard constraints on orthogonality can negatively affect the speed of convergence and model performance. Bio: I am a PhD student with professors Chris Pal and Samuel Kadoury at École Polytechnique de Montréal and MILA. I am working on medical image segmentation models and have recently begun developing an interest in optimization and regularization of deep neural networks. Prior to MILA, I studied Engineering Science at the University of Toronto, specializing in biomedical engineering. An aspect of computer science that appealed to me is the fast production of experimental results -- unfortunately, I also like big models. --Junyoung

1 3

[TeaTalk] Ethan Perez, July 14, AA6214, 13:45
by Dzmitry Bahdanau 14 Jul '17

14 Jul '17

Hi all, Our next speaker is Ethan Perez, who is currently interning at MILA with Aaron Courville. Please come to AA6214 on July 14 at 13:45! *Title:* Learning Visual Reasoning Without Strong Priors *Abstract:* Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Standard deep learning approaches tend to exploit biases in the data rather than learn this underlying structure, while leading methods learn to visually reason successfully but are hand-crafted for reasoning. We show that a general-purpose, Conditional Batch Normalization method achieves state-of-the-art results on the Compositional Language and Elementary Visual Reasoning (CLEVR) task with a 2.4% error rate. We outperform the next best end-to-end method (4.5%) which uses data augmentation and even methods that use extra supervision (3.1%). We probe our model to shed light on how it reasons, showing it has learned a question-dependent, multi-step process. Previous work has operated under the assumption that visual reasoning calls for a specialized architecture, but we show that a general architecture with proper conditioning can learn to visually reason effectively. *Bio:* Ethan Perez is a rising 4th year computer science undergrad at Rice University. He is currently interning at MILA working with Aaron Courville on Visual Reasoning. Previously, he has researched on deep semi-supervised learning methods and built machine learning models for location detection at Google Maps and fraud detection at Uber. Dima

2 2

Seminar in statistics and Monte Carlo Thursday July 13, 10h45
by Pierre L'Ecuyer 12 Jul '17

12 Jul '17

A seminar of interest for people in machine learning and in statistics: https://www.gerad.ca/fr/events/1479 -- Pierre L'Ecuyer, Professeur Titulaire Chaire du Canada en Simulation et Optimisation Stochastique CIRRELT, GERAD, and DIRO, Université de Montréal, Canada http://www.iro.umontreal.ca/~lecuyer

1 0

[TeaTalk] Rémi Leblond & Jean-Baptiste Alayrac, July 7, AA6214, 13:45
by Dzmitry Bahdanau 07 Jul '17

07 Jul '17

Hi all, For those of wondering if there will be a tea-talk this Friday I have good news - the answer is yes! Our next speakers will be Rémi Leblond and Jean-Baptiste Alayrac, both PhD students at INRIA, working with Simon Lacoste-Julien. Please come to AA6214 on July 7 at 13:45! Please find more information below: 1) Searnn, Rémi Leblond *Title:* SeaRNN: Training RNNs with Global-Local Losses *Abstract:* We propose SEARNN, a novel training algorithm for recurrent neural networks (RNNs) inspired by the “learning to search” (L2S) approach to structured prediction. RNNs have been widely successful in structured prediction applications such as machine translation or parsing, and are commonly trained using maximum likelihood estimation (MLE). Unfortunately, this training loss is not always an appropriate surrogate for the test error: by only maximizing the ground truth probability, it fails to exploit the wealth of information offered by structured losses. Further, it introduces discrepancies between training and predicting (such as exposure bias) that may hurt test performance. Instead, SEARNN leverages test-alike search space exploration to introduce global-local losses that are closer to the test error. We demonstrate improved performance over MLE on three different tasks: OCR, spelling correction and text chunking. Finally, we propose a subsampling strategy to enable SEARNN to scale to large vocabulary sizes. *Bio:* Rémi is a second year Ph.D. student at INRIA in the SIERRA team under the supervision of Simon Lacoste-Julien <http://www.di.ens.fr/~slacoste/>. He's interested in very large scale optimization for new complex machine learning models. His current focus is on parallel and distributed algorithms and structured prediction using neural networks. After graduating from Ecole Polytechnique <https://www.polytechnique.edu/> and Corps des Mines (French MPA), he worked in the Big Data field for three years, as a Data Scientist at SpotRight <http://spotright.com/> in the US (2011-2012) and as a Data Engineer at the Ministry of Defense (2013-2015). 2) Joint discovery of objects and manipulation actions, JB Alayrac *Title:* Joint discovery of objects and manipulation actions *Abstract:* Many human activities involve object manipulations aiming to modify the object state. Examples of common state changes include full/empty bottle, open/closed door, and attached/detached car wheel. In this work, we seek to automatically discover the states of objects and the associated manipulation actions. Given a set of videos for a particular task, we propose a joint model that learns to identify object states and to localize state-modifying actions. Our model is formulated as a discriminative clustering cost with constraints. We assume a consistent temporal order for the changes in object states and manipulation actions, and introduce new optimization techniques to learn model parameters without additional supervision. We demonstrate successful discovery of seven manipulation actions and corresponding object states on a new dataset of videos depicting real-life object manipulations. We show that our joint formulation results in an improvement of object state discovery by action recognition and vice versa. *Bio:* Jean-Baptiste Alayrac received the MS degree in computer science in Ecole Normale Superieure (ENS), in Paris in 2014. He is currently working toward the PhD degree in the research teams WILLOW and SIERRA at INRIA Paris under the supervision of Josef Sivic, Ivan Laptev and Simon Lacoste-Julien. His research focuses on structured prediction from vision and natural language. Dima

1 2

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

Lisa_seminaires Juillet 2017