Lisa_teatalk

Télécharger

lisa_teatalk@iro.umontreal.ca

Octobre 2010

1 participants
2 discussions

Tea Talk tomorrow (possibly)!
by Aaron Courville 14 Oct '10

14 Oct '10

Hi Gang, Tomorrow, if he's feeling up to it, Dumitru Erhan will regale us with stories of working at Google. When: Thursday Oct 14th @ 14h30 (Unless Dumi is still sick) Where: LISA Lab (AA3256) Title: How to model high-resolution images by starting with smaller patches first? Abstract: I'll go over some experiments and explorations of this topic, which I've done during the summer. While I'll present some results, this will be more of an open discussion on how to actually tackle this problem in a large-scale setting. Cheers, Aaron -- Aaron C. Courville Département d’Informatique et de recherche opérationnelle Université de Montréal email:Aaron.Courville@gmail.com

1 0

Fwd: [Lisa_seminaires] UdeM-McGill-MITACS machine learning seminar Thu Oct. 7@14h00, AA-3195
by Aaron Courville 05 Oct '10

05 Oct '10

Hi All, Charles Cadieu is visiting the lab tomorrow and Thursday (see below for details of his talk on Thursday at 14h00). Please let me know when you are *not available* to meet with him over these two days. Also let me know if you would particularly like to meet with him so that I can be sure to fit you into his schedule. Cheers, Aaron ---------- Forwarded message ---------- From: Dumitru Erhan <erhandum(a)iro.umontreal.ca> Date: Fri, Oct 1, 2010 at 10:06 AM Subject: [Lisa_seminaires] UdeM-McGill-MITACS machine learning seminar Thu Oct. 7@14h00, AA-3195 To: lisa_seminaires(a)iro.umontreal.ca The UdeM-McGill-MITACS machine learning seminar series is back with an exciting fall schedule. Next week's seminar (see http://www.iro.umontreal.ca/article.php3?id_article=107&lang=en) Learning Spatial and Transformational Invariants for Visual Representation by Charles Cadieu Redwood Center for Theoretical Neuroscience University of California, Berkeley Location: Pavillon André-Aisenstadt (UdeM), room AA-3195 Time: Thursday, October 7, 14:00 Abstract: Learning abstract, invariant properties of the visual word is a key attribute of biological vision systems. I will describe a hierarchical, probabilistic model that learns to extract invariant spatial structure and invariant motion structure from movies of the natural environment. The first layer in the model produces a sparse decomposition of local edge and motion structure. This decomposition is achieved through a complex-valued sparse coding model in which amplitudes represent the presence of edge structure at specific positions, orientations, and spatial scales, and phases represent the precise positions of edges and how image structure changes through time. This decomposition into amplitude and phase exposes statistical dependencies that the top layer in the model captures as two types of invariances: spatial and transformational. The spatial invariants are a sparse code of the patterns in the first layer amplitude components. They code a rich set of multi-scale edges, textures, and texture defined edge boundaries. The transformational invariants are a sparse representation of patterns of change in the first layer phase components. They learn a multi-scale code of motion, spanning local and global motions, and are capable of learning complex motions such as zooming, rotation, and deformation. Besides extracting abstract, invariant properties of the visual world, I will show how the hierarchical model provides a concrete model of cortical feedback that is useful for perception under noisy or ambiguous conditions. _______________________________________________ Lisa_seminaires mailing list Lisa_seminaires(a)mercure.iro.umontreal.ca https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_seminaires -- Aaron C. Courville Département d’Informatique et de recherche opérationnelle Université de Montréal email:Aaron.Courville@gmail.com

1 0