Lisa_seminaires Octobre 2007

lisa_seminaires@iro.umontreal.ca

5 participants
6 discussions

UdeM-McGill-MITACS machine learning seminar Fri Nov. 2, 11:30am, MC 437
by Hugo Larochelle 30 Oct '07

30 Oct '07

This week's seminar (see http://www.iro.umontreal.ca/article.php3? id_article=107&lang=en): Preliminary steps toward a probabilistic, decision theoretic model of dynamic scene understanding by Nando de Freitas Computer Science Department University of british Columbia Location: Mc Gill, McConnell engineering building room 437 Time: November 2nd 2007, 11:30am Abstract: It is widely agreed that efficient visual search requires the integration of target-driven top-down information and image-driven bottom-up information. Yet the problem of gaze planning - that is, selecting the next best gaze location given the current observations - remains largely unsolved. We propose a probabilistic system that models the gaze sequence as a finite-horizon Bayesian sequential decision process. Direct policy search is used to reason about the next best gaze locations. The system integrates bottom-up saliency information, top-down target knowledge and additional context information through principled Bayesian priors. This results in proposal gaze locations that depend not only the feature visual saliency, but also on prior knowledge and the spatial likelihood of locating the target. The system has been implemented using state-of-the-art object detectors and evaluated on a real-world dataset by comparing it to gaze sequences proposed by a pure bottom-up saliency-based process and to an object detection approach that analyzes the full image. The target-directed attention system is shown to result in higher object detection precision than both competitors, to attend to more relevant targets than the bottom-up attention system, and to require significantly less computation time than the exhaustive approach. This is joint work with Julia Vogel.

1 0

REMINDER: UdeM-McGill-MITACS machine learning seminar, PAA 1409 (UdeM), Fri Oct 19, 11:30am
by Hugo Larochelle 25 Oct '07

25 Oct '07

This week's seminar (see http://www.iro.umontreal.ca/article.php3? id_article=107&lang=en): Learning the 2-D Topology of Images by Pascal Lamblin, Département d’Informatique et Recherche Opérationnelle Université de Montréal Location: Pavillon André-Aisenstadt (UdeM), room 1409 Time: October 19th 2007, 11h30 We study the following question: is the two-dimensional structure of images a very strong prior or is it something that can be learned with a few examples of natural images? If someone gave us a learning task involving images for which the two-dimensional topology of pixels was not known, could we discover it automatically and exploit it? For example suppose that the pixels had been permuted in a fixed but unknown way, could we recover the relative two-dimensional location of pixels on images? The surprising result presented here is that not only the answer is yes but that about as few as a thousand images are enough to approximately recover the relative locations of about a thousand pixels. This is achieved using a manifold learning algorithm applied to pixels associated with a measure of distributional similarity between pixel intensities. We compare different topology-extraction approaches and show how having the two-dimensional topology can be exploited.

2 1

UdeM-McGill-MITACS machine learning seminar, PAA 1409 (UdeM), Fri Oct 19, 11:30am
by Hugo Larochelle 17 Oct '07

17 Oct '07

This week's seminar (see http://www.iro.umontreal.ca/article.php3?id_article=107&lang=en): Learning the 2-D Topology of Images by Pascal Lamblin, Département d’Informatique et Recherche Opérationnelle Université de Montréal Location: Pavillon André-Aisenstadt (UdeM), room 1409 Time: October 19th 2007, 11h30 We study the following question: is the two-dimensional structure of images a very strong prior or is it something that can be learned with a few examples of natural images? If someone gave us a learning task involving images for which the two-dimensional topology of pixels was not known, could we discover it automatically and exploit it? For example suppose that the pixels had been permuted in a fixed but unknown way, could we recover the relative two-dimensional location of pixels on images? The surprising result presented here is that not only the answer is yes but that about as few as a thousand images are enough to approximately recover the relative locations of about a thousand pixels. This is achieved using a manifold learning algorithm applied to pixels associated with a measure of distributional similarity between pixel intensities. We compare different topology-extraction approaches and show how having the two-dimensional topology can be exploited.

1 0

Fwd: [dgi-seminaires] séminaire GIGL
by Yoshua Bengio 15 Oct '07

15 Oct '07

Begin forwarded message: > From: Gilles Pesant <Gilles.Pesant(a)polymtl.ca> > Date: October 15, 2007 8:25:06 AM EDT (CA) > To: dgi-seminaires(a)liste.polymtl.ca > Subject: [dgi-seminaires] séminaire GIGL > > SÉMINAIRE DU GIGL > > Titre: La création de l’avenir des multimédias interactifs > > Conférencier(ère): Christopher Pal (U. Rochester) > > Date: jeudi le 18 octobre de 11h30 à 12h20 > Lieu: L-4812, pavillon Lassonde de l'École Polytechnique > (campus de l'Université de Montréal) > > > RÉSUMÉ > > Notre capacité de capturer les informations a atteint des niveaux > sans précédent. Une manière puissante pour organiser et faciliter > les interactions avec ce déluge d'information est de créer de > nouvelles formes de multimédias interactifs. Pour cette > présentation, je démontrerai comment les modèles probabilistes et > les méthodes d'optimisation sont employés pour créer le noyau des > technologies qui permettent la création de nouvelles formes de > médias numériques (visuels) interactifs. > Je me concentrerai sur les méthodes et algorithmes pour utiliser > des représentations visuelles en tant qu'interfaces interactives > pour accéder aux informations. Je présenterai les tâches facilitant > la création des représentations interactives à haute résolution de > scènes visuelles, telles que les algorithmes pour les appareils > photo numériques interactifs ou pour les représentations virtuelles > de la Terre. J’illustrerai comment intégrer de multiples images > pour créer des représentations panoramiques de haute qualité et je > démontrerai une façon de prédire la structure tridimensionnelle de > scènes visuelles en utilisant une série d’images. En examinant les > étapes pour associer l'information sémantique des textes à ces > représentations visuelles riches, je montrerai comment des modèles > probabilistes basés sur les champs conditionnels aléatoires sont > employés pour classifier les documents et pour extraire > l'information sémantique. Je soulignerai mes contributions au > niveau de la construction de structures de modèles innovateurs et > de méthodes innovatrices pour optimiser les champs conditionnels > aléatoires. > > Pour plus d'information, > contactez Gilles Pesant (340-4711 poste 4142 ou > gilles.pesant(a)polymtl.ca) >

1 0

[Fwd: Another Math-Neuro talk: Oct 9th]
by Yoshua Bengio 02 Oct '07

02 Oct '07

-------- Original Message -------- Subject: Another Math-Neuro talk: Oct 9th Date: Tue, 2 Oct 2007 15:03:15 -0400 From: Paul Cisek <paul.cisek(a)umontreal.ca> Hello, We are going to have another math-neuro presentation next week, on Tuesday Oct 9th, from 14h00-15h00 in room 4106. The presentation will be by Jean-Phillippe Thivierge, who is briefly visiting from Indiana (I apologize for doing this on a Tuesday before the "travaux récents", but it was the only possible time). Here's an abstract: "How Random is Brain Activity?" "Neurons of several regions of the brain, including hippocampus and cortex, have a tendency to spontaneously alternate between states of activity and quiescence at non-periodic, seemingly random times. Despite the ubiquitous nature of this phenomenon across species and protocols, the mechanisms responsible remain largely unknown. Using computer simulations, we show that spontaneous synchronization can emerge naturally from completely deterministic cellular interactions, without randomness. Noise-free simulations capture the Poisson-like distribution of both spontaneous and evoked activity recorded in acute CA1 slices of hippocampus, and suggest new experiments and their expected outcome. This talk is hoped to generate some interesting discussions among neurophysiologists and modelers." Regards, Paul ----------------------------------------------- Paul Cisek, Ph.D. Department of physiology, room 4141 University of Montreal C.P. 6128 Succursale Centre-ville Montreal QC H3C 3J7 Canada phone: 514-343-6111 x4355 FAX: 514-343-2111 email: paul.cisek(a)umontreal.ca <mailto:paul.cisek@umontreal.ca> ----------------------------------------------- -- Yoshua Bengio

1 0

[Fwd: Math-Neuro lecture on Oct 4th: Basal Ganglia and Reinforcement Learning]
by Yoshua Bengio 01 Oct '07

01 Oct '07

-------- Message original -------- Sujet: Math-Neuro lecture on Oct 4th: Basal Ganglia and Reinforcement Learning Date: Mon, 1 Oct 2007 12:55:15 -0400 De: Paul Cisek <paul.cisek(a)umontreal.ca> Répondre à :: Paul Cisek <paul.cisek(a)umontreal.ca> Hello everyone, This Thursday, we will have a Math-Neuro meeting in which Francois Rivest will give us a presentation on models of reinforcement learning. Here is the abstract: "Over the past 10 years, a set of computationnel models coming from reinforcement learning have gained popularity in modeling of dopaminergic neurons phasic signal (Montague, Schultz, Daw, & others). These models allow making a number of hypotheses about possible roles of the basal ganglia (especially striatum) and about local plasticity. In this presentation, I will introduce the actor-critic temporal-difference learning family of algorithm that has been used to model the phasic dopaminergic neuron signal. I will concentrate on explaining how this algorithm works with minimal mathematics, and as many examples as possible. I hope to generate some discussion with people working on dopaminergic or basal ganglia neurons." Our meeting will take place in room 1120 of Pavillon Paul-Desmarais (2960 chemin de la tour) from 13h30 to 15h00 on Thursday, October 4th. Hope to see you there, Paul P.S. Trevor, Louis-Eric, Peter: I thought you and/or your students might be interested as well. ----------------------------------------------- Paul Cisek, Ph.D. Department of physiology, room 4141 University of Montreal C.P. 6128 Succursale Centre-ville Montreal QC H3C 3J7 Canada phone: 514-343-6111 x4355 FAX: 514-343-2111 email: paul.cisek(a)umontreal.ca <mailto:paul.cisek@umontreal.ca> -----------------------------------------------

1 0

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

Lisa_seminaires Octobre 2007