Lisa_seminaires Janvier 2012

lisa_seminaires@iro.umontreal.ca

3 participants
5 discussions

Fwd: Colloque du DIRO, mardi 31 janv, 11h15
by Frédéric Bastien 30 Jan '12

30 Jan '12

---------- Forwarded message ---------- From: Pierre L'Ecuyer <lecuyer(a)iro.umontreal.ca> Date: 2012/1/30 Subject: Colloque du DIRO, mardi 31 janv, 11h15 To: seminaires <seminaires(a)iro.umontreal.ca>, liste(a)gerad.ca, communications(a)cirrelt.ca Colloque du DIRO: Mardi le 31 janvier 2012 Heure: 11h15 Salle: 5340, Pavillon André-Aisensdadt Conférencier: Aaron Courville, LISA, DIRO, Université de Montréal Titre: Modèles "Spike-and-Slab" d'images naturelles (Spike-and-Slab models of natural images) Résumé et annonce imprimable Page web des colloques: http://www.iro.umontreal.ca/~lecuyer/colloque-H12.html -- 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

Fwd: Boltzmann machines, speech applications
by Yoshua Bengio 25 Jan '12

25 Jan '12

Begin forwarded message: > From: "Kenny Patrick" <patrick.kenny(a)crim.ca> > Subject: Boltzmann machines, speech applications > Date: 25 janvier 2012 13:29:11 HNE > To: "Richard Rose" <rose(a)ece.mcgill.ca>, "Tiago H. Falk" <falk(a)emt.inrs.ca>, Pierre.Dumouchel(a)etsmtl.ca, O'Shaughnessy(a)crim.ca, Douglas <dougo(a)emt.inrs.ca>, hugo.larochelle(a)usherbrooke.ca, bengioy(a)iro.umontreal.ca > Cc: recostag(a)corpo.crim.ca, reco(a)crim.ca, Langis.Gagnon(a)crim.ca > > Hello everybody > > I am planning to give a series of 3 talks at CRIM on recent developments in Boltzmann mahcines, deep belief nets and deep neural nets with applications to speech processing. The target audience is primarily researchers and PhD students working in speech recognition or speaker recognition. > > I aim to explain > > (i) how to build the deep neural networks for speech recognition that enabled Microsoft to achieve the results reported in the > 2011 Interspeech paper by Seide and colleagues > > (ii) how Boltzmann machines might be used to replace the generative models currently used in speaker recognition (the universal background model, the ivector extractor, probabilistic linear discriminant analysis and the cosine distance metric) > > I will assume that the audience is familiar with basic probability (I will begin by reviewing variational Bayes and expectation maximization) but not necessarily the machine learning literature. > > I will distribute notes on these topics: > > (i) Boltzmann machines, Salakhuditnov's algorithms > > (ii) Sigmoid belief networks > > (iii) Hinton's construction of deep belief nets, backpropagation > > Tentatively, I propose giving these talks at 4 p.m. on Monday, Wedensday and Friday, February 6, 8 and 10. > > If any of your students are interested please have them get in touch with me so that we can sort out any scheduling conflicts and I can confirm the final arrangements. > > cheers > > Patrick > > ________________________________________________ > Patrick Kenny > Chercheur Principal > CRIM > 405, avenue Ogilvy, bureau 101 > Montréal (Québec) H3N 1M3 > Tél.: 514 840 1235 x 4624 > Fax : 514 840 1244 > Patrick.Kenny(a)crim.ca > www.crim.ca > http://www.crim.ca/perso/patrick.kenny

1 0

Fwd: [SIGMM] 2nd Audio/Visual Emotion Challenge and Workshop (AVEC 2012)
by Yoshua Bengio 25 Jan '12

25 Jan '12

Could be interesting for some of us: submission deadline July 21st. Begin forwarded message: > From: Bjoern Schuller <schuller(a)tum.de> > Subject: [SIGMM] 2nd Audio/Visual Emotion Challenge and Workshop (AVEC 2012) > Date: 24 janvier 2012 16:27:34 HNE > To: undisclosed-recipients:; > > Dear List, > > We would like to bring to your attention the2nd International Audio/Visual Emotion Challenge and Workshop (AVEC2012), organised in conjunction with ACM ICMI2012 this year. See below for the CFP - apologies for potential cross-posting. > > _____________________________________________________________ > > Call for Participation / Papers > > 2nd International Audio/Visual Emotion Challenge and Workshop (AVEC 2012) > > in conjunction with ACM ICMI 2012, October 22-26, Santa Monica, California, USA > > http://sspnet.eu/avec2012/ > http://www.acm.org/icmi/2012/ > > Register and download data and features: > http://avec-db.sspnet.eu/accounts/register/ > > _____________________________________________________________ > > Scope > > The Audio/Visual Emotion Challenge and Workshop (AVEC 2012) will be the second competition event aimed at comparison of multimedia processing and machine learning methods for automatic audio, visual and audiovisual emotion analysis, with all participants competing under strictly the same conditions. The goal of the Challenge is to provide a common benchmark test set for individual multimodal information processing and to bring together the audio and video emotion recognition communities, to compare the relative merits of the two approaches to emotion recognition under well-defined and strictly comparable conditions and establish to what extent fusion of the approaches is possible and beneficial. A second motivation is the need to advance emotion recognition systems to be able to deal with naturalistic behavior in large volumes of un-segmented, non-prototypical and non-preselected data as this is exactly the type of data that both multimedia retrieval and human-machine/human-robot communication interfaces have to face in the real world. > > We are calling for teams to participate in emotion recognition from acoustic audio analysis, linguistic audio analysis, video analysis, or any combination of these. As benchmarking database the SEMAINE database of naturalistic video and audio of human-agent interactions, along with labels for four affect dimensions will be used. Emotion will have to be recognized in terms of continuous time, continuous valued dimensional affect in the dimensions arousal, expectation, power and valence. Two Sub-Challenges are addressed: The Word-Level Sub-Challenge requires participants to predict the level of affect at word-level and only when the user is speaking. The Fully Continuous Sub-Challenge involves fully continuous affect recognition, where the level of affect has to be predicted for every moment of the recording. > > Besides participation in the Challenge we are calling for papers addressing the overall topics of this workshop, in particular works that address the differences between audio and video processing of emotive data, and the issues concerning combined audio-visual emotion recognition > > Topics include, but are not limited to: > > Audio/Visual Emotion Recognition: > . Audio-based Emotion Recognition > . Linguistics-based Emotion Recognition > . Video-based Emotion Recognition > . Social Signals in Emotion Recognition > . Multi-task learning of Multiple Dimensions > . Novel Fusion Techniques as by Prediction > . Cross-corpus Feature Relevance > . Agglomeration of Learning Data > . Semi- and Unsupervised Learning > . Synthesized Training Material > . Context in Audio/Visual Emotion Recognition > . Multiple Rater Ambiguity > > Application: > . Multimedia Coding and Retrieval > . Usability of Audio/Visual Emotion Recognition > . Real-time Issues > > > Important Dates > ___________________________________________ > > Paper submission > July 21, 2012 > > Notification of acceptance > August 6, 2012 > > Camera ready paper and final challenge result submission > August 15, 2012 > > Workshop > October 22 or 26, 2012 > > > Organisers > ___________________________________________ > > Björn Schuller (Tech. Univ. Munich, Germany) > Michel Valstar University of Nottingham, UK) > Roddy Cowie (Queen's University Belfast, UK) > Maja Pantic (Imperial College London, UK) > > > Program Committee > ___________________________________________ > > Elisabeth André, Universität Augsburg, Germany > Anton Batliner, FAU Erlangen-Nuremberg, Germany > Felix Burkhardt, Deutsche Telekom, Germany > Fang Chen, NICTA, Australia > Mohamed Chetouani, UPMC, France > Laurence Devillers, U. Paris-Sorbonne 4, France > Julien Epps, University of New South Wales, Australia > Anna Esposito, IIASS, Italy > Raul Fernandez, IBM, USA > Roland Göcke, Australian National Univ., Australia > Hatice Gunes, Queen Mary University London, UK > Julia Hirschberg, Columbia University, USA > Aleix Martinez, Ohio State University, USA > Marc Méhu, University of Geneva, Switzerland > Marcello Mortillaro, University of Geneva, Switzerland > Matti Pietikainen, University of Oulu, Finland > Peter Robinson, University of Cambridge, UK > Stefan Steidl, FAU Erlangen-Nuremberg, Germany > Jianhua Tao, Chinese Academy of Sciences, China > Fernando de la Torre, Carnegie Mellon University, USA > Mohan Trivedi, Univ. of California San Diego, USA > Matthew Turk, Univ. of California Santa Barbara, USA > Alessandro Vinciarelli, University of Glasgow, UK > Rama Chellappa, University of Maryland, USA > Stefanos Zafeiriou, Imperial College London, UK > > > Please regularly visit our website http://sspnet.eu/avec2012 for more information and excuse cross-postings, > > > Thank you very much and all the best, > > > > Björn Schuller, Roddy Cowie, Maja Pantic, and Michel Valstar > > > > ___________________________________________ > > Dr. Björn Schuller > Senior Lecturer > > Technische Universität München > Institute for Human-Machine Communication > D-80333 München > Germany > +49-(0)89-289-28548 > > schuller(a)tum.de > www.mmk.ei.tum.de/~sch > ___________________________________________ > > > > > > _______________________________________________ > SIGMM mailing list > SIGMM(a)pi4.informatik.uni-mannheim.de > http://pi4.informatik.uni-mannheim.de/mailman/listinfo/sigmm

1 0

Fwd: MITACS Seminar January 27, 2012: John Langford, Yahoo Research
by Yoshua Bengio 25 Jan '12

25 Jan '12

FYI there is also going to be another very interesting talk at McGill on Feb. 10th 11am, by John Tsitsiklis. -- Yoshua Begin forwarded message: > From: "Michael Rabbat, Prof." <michael.rabbat(a)mcgill.ca> > Subject: Re: MITACS Seminar January 27, 2012: John Langford, Yahoo Research > Date: 25 janvier 2012 09:44:56 HNE > To: Yoshua Bengio <bengioy(a)iro.umontreal.ca> > > Thanks for forwarding. Too bad! The next upcoming seminar we have is John Tsitsiklis on Fri Feb 10 (probably also at 11am). I'll send more details (room, title, abstract, …) when I have them. > > Mike > > > > On 2012-01-24, at 10:21 PM, Yoshua Bengio wrote: > >> >> That is really too bad, but I wont't make it. I'll forward this, though. >> >> -- Yoshua >> >> On 2012-01-23, at 11:13, Michael Rabbat, Prof. wrote: >> >>> Hi Yoshua, >>> >>> Hope all's going well. John Langford will be in town this Friday and is giving a seminar at 11am here. Hope you can make it. Also, we'll be going for lunch afterwards and you're more than welcome to join us. Let me know. >>> >>> Cheers, >>> >>> Mike >>> >>> >>> >>> >>> Begin forwarded message: >>> >>> From: "Carrie Serban, Ms." <carrie.serban(a)mcgill.ca<mailto:carrie.serban@mcgill.ca>> >>> Subject: MITACS Seminar January 27, 2012: John Langford, Yahoo Research >>> Date: 23 January, 2012 11:10:30 AM EST >>> To: "Carrie Serban, Ms." <carrie.serban(a)mcgill.ca<mailto:carrie.serban@mcgill.ca>> >>> >>> Good morning, >>> >>> The next MITACS seminar will be held as follows: >>> >>> Reliable Effective Terascale Linear Learning >>> Dr. John Langford >>> Doctor of Learning, Yahoo Research >>> >>> Friday, January 27, 2012 >>> 11:00 – 12:30 >>> McGill University, McConnell Engineering building, room 603 >>> >>> Kindly forward to any students or colleagues who might be interested. >>> >>> Thanks very much. >>> Best regards, >>> Carrie >>> >>> Carrie Serban >>> Administrative Coordinator >>> SYTACom >>> McGill University >>> (514) 398-8104 >>> carrie.serban(a)mcgill.ca<mailto:carrie.serban@mcgill.ca> >>> >>> >>> <Abstract Langford.pdf> >> >

1 0

Fwd: MITACS Seminar January 27, 2012: John Langford, Yahoo Research
by Yoshua Bengio 24 Jan '12

24 Jan '12

Begin forwarded message: > Begin forwarded message: > > From: "Carrie Serban, Ms." <carrie.serban(a)mcgill.ca<mailto:carrie.serban@mcgill.ca>> > Subject: MITACS Seminar January 27, 2012: John Langford, Yahoo Research > Date: 23 January, 2012 11:10:30 AM EST > To: "Carrie Serban, Ms." <carrie.serban(a)mcgill.ca<mailto:carrie.serban@mcgill.ca>> > > Good morning, > > The next MITACS seminar will be held as follows: > > Reliable Effective Terascale Linear Learning > Dr. John Langford > Doctor of Learning, Yahoo Research > > Friday, January 27, 2012 > 11:00 – 12:30 > McGill University, McConnell Engineering building, room 603 > > Kindly forward to any students or colleagues who might be interested. > > Thanks very much. > Best regards, > Carrie > > Carrie Serban > Administrative Coordinator > SYTACom > McGill University > (514) 398-8104 > carrie.serban(a)mcgill.ca<mailto:carrie.serban@mcgill.ca> > >

1 0

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

Lisa_seminaires Janvier 2012