Mai 2012 - Lisa_seminaires - mailman.iro.umontreal.ca

Fwd: (reminder / change of room) UdeM-McGill Machine Learning Seminar: Geoffrey Hinton - Thurs, 17th @1500, AA1355
by Guillaume Desjardins 17 Mai '12

17 Mai '12

This is a reminder for tomorrow's talk by Geoff Hinton. *Please note the change of room*. The talk will now take place in pavillon Andre-Aisenstadt, room 1355 (which should accomodate more people). ---------- Forwarded message ---------- From: Guillaume Desjardins <guillaume.desjardins(a)gmail.com> Date: Mon, May 14, 2012 at 2:32 PM Subject: UdeM-McGill Machine Learning Seminar: Geoffrey Hinton - Thurs, 17th @1500 To: "lisa_seminaires(a)iro.umontreal.ca" <lisa_seminaires(a)iro.umontreal.ca> I am pleased to announce this upcoming talk by none other than Geoffrey Hinton, entitled "Does the brain do inverse graphics?". The talk will take place at the Universite de Montreal, pavillon Andre-Aisenstadt, room 5340, this Thursday, May 17th from 15:00-16:00. Hope to see you there! Title: Does the brain do inverse graphics? Abstract: --------- Recognizing a familiar shape from the pattern of light intensities on the retina is difficult because changes in viewpoint can dramatically change the pattern of light intensities. The general belief among both neuroscientists and neural network modelers is that the infero-temporal pathway copes with viewpoint variation by using multiple levels of representation in which each level is slightly more viewpoint-invariant than the level below. Unfortunately, this approach cannot explain how we can be acutely sensitive to the precise spatial relationships between high-level parts such as a nose and a mouth. >From an engineering perspective, the natural way to deal with spatial relationships is to associate a vector of pose parameters with each recognized part and to make use of the fact that spatial relationships can then be modeled very efficiently using linear operations. This is what is done in computer graphics and it is the reason why computer graphics can deal with changes in viewpoint so easily. Despite the long history of generative models of perception, computational neuroscientists have not taken this aspect of computer graphics seriously, possibly because they do not believe that the brain can do linear algebra. I shall show how a neural net can learn to extract parts with explicit pose parameters from an image and how this makes it very easy to recognize spatial configurations of parts under a very wide range of viewpoints. I shall then sketch a way in which the brain could use spike timing to implement the required linear algebra very efficiently. About the speaker: Geoffrey Hinton designs machine learning algorithms. His aim is to discover a learning procedure that is efficient at finding complex structure in large, high-dimensional datasets and to show that this is how the brain learns to see. His contributions include back-propagation, Boltzmann machines, distributed representations, mixtures of experts, variational learning, and deep belief nets. His current research uses local .capsules.. composed of a few hundred neurons that perform complicated internal computations on their inputs and encapsulate the results into a small vector of highly informative outputs that reveal the hidden structure in the data.

1 0

UdeM-McGill Machine Learning Seminar: Geoffrey Hinton - Thurs, 17th @1500
by Guillaume Desjardins 15 Mai '12

15 Mai '12

I am pleased to announce this upcoming talk by none other than Geoffrey Hinton, entitled "Does the brain do inverse graphics?". The talk will take place at the Universite de Montreal, pavillon Andre-Aisenstadt, room 5340, this Thursday, May 17th from 15:00-16:00. Hope to see you there! Title: Does the brain do inverse graphics? Abstract: --------- Recognizing a familiar shape from the pattern of light intensities on the retina is difficult because changes in viewpoint can dramatically change the pattern of light intensities. The general belief among both neuroscientists and neural network modelers is that the infero-temporal pathway copes with viewpoint variation by using multiple levels of representation in which each level is slightly more viewpoint-invariant than the level below. Unfortunately, this approach cannot explain how we can be acutely sensitive to the precise spatial relationships between high-level parts such as a nose and a mouth. >From an engineering perspective, the natural way to deal with spatial relationships is to associate a vector of pose parameters with each recognized part and to make use of the fact that spatial relationships can then be modeled very efficiently using linear operations. This is what is done in computer graphics and it is the reason why computer graphics can deal with changes in viewpoint so easily. Despite the long history of generative models of perception, computational neuroscientists have not taken this aspect of computer graphics seriously, possibly because they do not believe that the brain can do linear algebra. I shall show how a neural net can learn to extract parts with explicit pose parameters from an image and how this makes it very easy to recognize spatial configurations of parts under a very wide range of viewpoints. I shall then sketch a way in which the brain could use spike timing to implement the required linear algebra very efficiently. About the speaker: Geoffrey Hinton designs machine learning algorithms. His aim is to discover a learning procedure that is efficient at finding complex structure in large, high-dimensional datasets and to show that this is how the brain learns to see. His contributions include back-propagation, Boltzmann machines, distributed representations, mixtures of experts, variational learning, and deep belief nets. His current research uses local .capsules.. composed of a few hundred neurons that perform complicated internal computations on their inputs and encapsulate the results into a small vector of highly informative outputs that reveal the hidden structure in the data.

2 1

Fwd: Séminaires conjoints du GERAD_14-15-16 mai | GERAD Joint Seminars_May 14, 15, 16
by Yoshua Bengio 10 Mai '12

10 Mai '12

Hi all, The announced talks by Paolo Caravani seem interesting: May 14 & 16, PAA 6516, 10h30. -- Yoshua Begin forwarded message: > From: Véronique Sage <sagev(a)iro.umontreal.ca> > Subject: Fwd: Séminaires conjoints du GERAD_14-15-16 mai | GERAD Joint Seminars_May 14, 15, 16 > Date: 9 mai 2012 13:34:01 HAE > To: Professeurs <profs(a)iro.umontreal.ca> > > Bonjour, > Pour votre information. > Véronique > > -------- Message original -------- > Sujet: Séminaires conjoints du GERAD_14-15-16 mai | GERAD Joint Seminars_May 14, 15, 16 > Date : Wed, 9 May 2012 11:59:38 -0400 > De : GERAD <info(a)gerad.ca> > Pour : <liste(a)gerad.ca> > > > ENGLISH FOLLOWS > > Bonjour, > > Vous trouverez, sur notre site Internet, les détails des prochains Séminaires conjoints Fondation HEC/Chaire théorie des jeux et gestion/GERAD. > > · Lundi 14 mai 2012 à 10h30 > Paolo Caravani, University of L’Aquila > Learning and Distributed Learning in Multi-Agent systems #1 > http://www.gerad.ca/fr/activites/seminaire.php?id=845 > > · Mardi 15 mai 2012 à 11 h > Micheal Grothe, Bielefeld University, Allemagne > Effects of Vertical Integration from a Dynamic Point of View > http://www.gerad.ca/fr/activites/seminaire.php?id=830 > > · Mercredi 16 mai 2012 à 10h30 > Paolo Caravani, University of L’Aquila > Learning and Distributed Learning in Multi-Agent systems #2 > http://www.gerad.ca/fr/activites/seminaire.php?id=846 > > > Ces séminaires seront présentés à la salle 6516 du pavillon André-Aisenstadt du campus de l’Université de Montréal. > > N’oubliez pas de les inscrire à votre agenda et de partager l’information avec vos collègues et amis. > > Merci et bons séminaires. > > ------------------------------------------------ > > Hello, > > On our Web site, you will find the details of the next Joint Seminars Fondation HEC/Chair in Game Theory and Management/GERAD. > > · Monday, May 14, 2012 at 10h30 > Paolo Caravani, University of L’Aquila > Learning and Distributed Learning in Multi-Agent systems #1 > http://www.gerad.ca/en/activities/seminar.php?id=845 > > · Tuesday, May 15, 2012 at 11 h > Micheal Grothe, Bielefeld University, Allemagne > Effects of Vertical Integration from a Dynamic Point of View > http://www.gerad.ca/en/activities/seminar.php?id=830 > > · Wednesday, May 16, 2012 at 10h30 > Paolo Caravani, University of L’Aquila > Learning and Distributed Learning in Multi-Agent systems #2 > http://www.gerad.ca/en/activities/seminar.php?id=845 > > > They will take place in room 6516 of the André-Aisenstadt building, on the campus of the Université de Montréal. > > Please write down the date and time of the seminars and pass along the word to your colleagues and friends. > > Thank you and have great seminars. > > ---- > L’équipe du GERAD/GERAD team > 514-340-6053 > info(a)gerad.ca

1 0