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

Tea-talk: clarification
by Christian Theriault 27 Nov '12

27 Nov '12

Hello LISA members. Thank you for listening :) A few clarifications on questions and things said today. There was indeed transductive learning in the video classification as suggested by Yoshua. This was somewhat inevitable when using the leave-one-out procedure. Even if the learning of slow features and the sampling were done on half the set, the SVM leave-one-out procedure trains and tests on all videos which will automatically contain the videos used for training the features. There is also the possibility of some sort of transductive learning on the first architecture (image classification). The sampling was done on a training set but the splits of the SVM were random. This allows for the possibility that a test image signature is computed with some filters learned on the very same image. There were 10 examples per class on the Maryland "in-the-wild" data set. Explaining the factor of 10 in the results. One last little detail, my master's degree was specialized in applied mathematics. At least it is entitled that way :) I believe that I mentioned just mathematics. Have a good evening LISA members !

1 0

Talk by Christian Theriault, Tuesday, November 27th, 3:30pm, room TBD.
by Guillaume Desjardins 26 Nov '12

26 Nov '12

Please join us on Tuesday for a talk by Christian Theriault. Title and abstract are below. The talk will be held in english, despite what the abstract would imply... When: Tuesday, November 27th, 3:30pm Where: Pavillon Aisenstadt, Room TBD (probably AA3195) Title: "Extended coding and pooling in the HMAX model" and "Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis" Summary: À ce Tea-talk, je vous présenterai un article sur la classification d'images à l'aide d'un réseau multicouche (publié dans IEEE, Trans. Image Processing) et un article sur la classification de vidéos (sousmis à IEEE CVPR).

1 1

meditation music for deep learning
by Yoshua Bengio 05 Nov '12

05 Nov '12

http://www.youtube.com/watch?v=qMncSCroKJU Very slow learning rate. But may actually converge to something very pure and abstract. Enjoy, -- Yoshua

1 0