The workshop “Learning Data Representation: Hierarchies and Invariance” will be held at the McGovern Institute for Brain Research at MIT (Bldg. 46) on November 22-24, 2013. The workshop will start Friday Nov. 22 afternoon and run until Sunday Nov. 24 at lunch. A reception dinner has been planned for Friday night. 

All workshop activities will take place at McGovern Institute for Brain Research, MIT Bldg 46-3002 (Singleton Auditorium), 43 Vassar Street, Cambridge, MA 02139 (directions).

Workshop Agenda

There will be four sessions, each one with a set of talks and a panel discussion. 

  • Session 1: Early Features in Vision
  • Session 2: Learning Features and Representations
  • Session 3: Learning Invariances and Hierarchies
  • Session 4: Beyond Feedforward Architectures
Schedule: pdf
Videos/slides: Use the links below for videos of the talks/panels (MIT TechTV) and presentation slides (kindly made available by all participants).

Friday November 22, 2013

MIT Bldg 46-3002, Singleton Auditorium

14:30 Introduction to the workshop | T. Poggio (video), L. Rosasco (video), (slides)

Session: Early Features in Vision | Chair: C. Tomasi

14:50 Filters and other potions for early vision and recognition | P. Perona (video) (slides)
15:30 Transformations in early vision from a symmetry argument | C. Stevens (video) (slides)
16:10 Break
16:40 Hierarchical models of the visual cortex | T. Serre (video*) (slides)
17:20 Panel discussion (video) | C. Tomasi [moderator] (video) (slides), W. Freeman (video) (slides), G. Sandini (video) (slides) + Speakers

8:00 Reception at "Catalyst Restaurant"
* video is not available due to technical issues with the recording  

Saturday November 23, 2013

MIT Bldg 46-3002, Singleton Auditorium

  8:30 am Breakfast

Session: Learning Features and Representations | Chair: A. Verri

  9:30 Latent structure beyond sparse codes | B. Recht (video) (slides)
10:10 Dictionary learning: 3+ snippets on learning features | G. Sapiro (video) (slides)
10:50 Break
11:20 Panel discussion (video) | A.Verri [moderator], L. Rosasco (video) (slides), M. Belkin (video) (slides), J. Buhmann (video) (slides) + Speakers

12:20 Lunch

Session: Learning Invariances and Hierarchies | Chair: J. DiCarlo

14:00 Learning invariant feature hierarchies | Y. LeCun (video) (slides)
14:50 Scattering bricks to build invariants for perception | S. Mallat (video pt.1, pt.2) (slides)
15:40 Break
16:10 M-theory | T. Poggio (video) (slides)
17:00 Panel discussion (video) | J. DiCarlo [moderator] (video) (slides), P. Baldi (video) (slides), M. Riesenhuber + Speakers

18:30 Dinner (up to individual participants)

Sunday November 24, 2013

MIT Bldg 46-3002, Singleton Auditorium

 8:30 am Breakfast

Session: Beyond Feedforward Architectures | Chair: J. Tenenbaum

  9:00 The role of mobility and control in the inference of representations | S. Soatto (video) (slides)
  9:40 Atoms of recognition | S. Ullman (video) (slides)
10:20 Break
10:50 Compositional models: complexity of representation and inference | A. Yuille (video) (slides)
11:30 Panel discussion (video) | J. Tenenbaum [moderator] (video) (slides), R. Salakhutdinov (video) (slides) + Speakers

12:30 Final remarks | T. Poggio (video) (slides)