Workshops

Language and Vision Workshop, CVPR 2015

Jun 11, 2015 - 9:00 am
CVPR 2015 logo
Venue:  Hynes Convention Center Address:  900 Boylston Street, Boston, MA 02115

Date: Thursday, June 11, 2015

Location: CVPR 2015, Hynes Convention Center, Boston, Massachusetts.

We're planning a day of invited speakers and a poster session. Submissions are non-archival short 2 page abstracts. Submission of both novel and already-published but relevant work is encouraged.

This workshop is co-organized by CBMM, Istituto Italiano di Tecnologia (IIT), MIT, Stanford University, UCLA, and the University of Surrey.

See the complete event details and videos here.

Organizer:  Andrei Barbu Georgios Evangelopoulos Daniel Harari

Workshop: Engineering and Reverse Engineering Reinforcement Learning

Jul 18, 2014 - 10:00 am
Engineering and Reverse Engineering Reinforcement Learning
Venue:  MIT: McGovern Institute Singleton Auditorium, 46-3002 Address:  43 Vassar Street, MIT Bldg 46, Cambridge, 02139 United States

Summary: Psychologists and neuroscientists routinely borrow ideas from machine learning to understand and model reinforcement learning in humans and animals. Likewise, ideas from psychology and neuroscience filter into machine learning in a variety of ways. The goal of the workshop is to highlight some of the theoretical synergies that have arisen from this cross-pollination. The symposium will cover three topics (see below), each addressed by one cognitive scientist/neuroscientist and one computer scientist.

Schedule:

10am-10:05am: Introduction and welcome

Session 1: Learning to learn
10:05-10:30: Michael Littman (Brown)
10:30-10:55: Michael Frank (Brown)
10:55-11:10: discussion

Session 2: Inverse reinforcement learning and theory of mind
11:10-11:35: Monica Babes-Vroman (Rutgers)
11:35-12:00: Chris Baker (MIT)
12:00-12:15: discussion

12:15-1:00: lunch

Session 3: Intrinsic motivation and exploration
1:00-1:25: Laura Schulz (MIT)
1:25-1:50: Andrew Barto (UMass Amherst)
1:50-2:05: discussion

Workshop is co-organized by the MIT Intelligence Initiative (MIT I^2) and the Center for Brains, Minds and Machines (CBMM.)

This workshop if free and open to the public. Registration required.

Regularization Methods for Machine Learning – RegML 2014, June 30, 2014 – July 4, 2104, Genoa, Italy

Jun 30, 2014 - 9:00 am
Address:  Genoa, Italy

CBMM Partners the Istituto Italiano di Tecnologia (IIT) and the University of Genova are organizing a machine learning course this summer in Genoa, Italy.

Regularization Methods for Machine Learning (RegML)

Instructors: Francesca Odone (francesca.odone [at] unige.it ); Lorenzo Rosasco (lorenzo.rosasco [at] unige.it)
Machine Learning PhD Summer Course in Genoa, Italy
June 30, 2104 – July 4, 2014

A 20 hours advanced machine learning course including theory classes and practical laboratory session. The course covers foundations as well as recent advances in Machine Learning with emphasis on high dimensional data and a core set techniques, namely regularization methods. In many respect the course is compressed version of the 9.520 course at MIT.

The course started in 2008 has seen an increasing national and international attendance over the years with a peak of 85 participants in 2013.

Registration required:  send an e-mail to the instructors (contact info listed above) by May 24th. The course will be activated if a minimum number of participants is reached.

The course will be held in Genova in the heart of the Italian Riviera.

Contact:
Dr. Lorenzo Rosasco
Assistant Professor, DIBRIS, Universita’ degli Studi di Genova
LCSL, Massachusetts Institute of Technology & Istituto Italiano di Tecnologia

LCSL — Laboratory for Computational and Statistical Learning

For more information>

Organizer:  Lorenzo Rosasco Organizer Email:  cbmm-contact@mit.edu

MLCC 2014 Machine Learning Crash Course

Feb 18, 2014 - 9:00 am
Porto Antico
Venue:  Dipartimento di Informatica, Bioingegneria, Robotica ed Ingegneria dei Sistemi Address:  Via all'Opera Pia, 13 Genova, 16145 Italy

Course organized by the POLITECMED cluster of Companies and Research Institutions in collaboration with the Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS), Center for Brain Minds and Machines (CBMM), and with the contribution of the European Regional Development Fund within the POR 2007-2013 of Regione Liguria.

The course will be held on February 18th-21th, 2014 at DIBRIS (University of Genoa, Italy.)

Machine Learning is a key to develop intelligent systems and analyze data in science and engineering. Machine Learning engines enable intelligent technologies such as Siri, Kinect or Google self driving car, to name a few. At the same time, Machine Learning methods help deciphering the information in our DNA and make sense of the flood of information gathered on the web, forming the basis of a new “Science of Data”. This course provides an introduction to the fundamental methods at the core of modern Machine Learning. It covers theoretical foundations as well as essential algorithms. Classes on theoretical and algorithmic aspects are complemented by practical lab sessions.

 For more information >

Workshop on Broadening Participation in the Science of Intelligence

Jan 8, 2014 - 9:00 am
Venue:  Massachusetts Institute of Technology: MIT Address:  77 Massachusetts Ave Cambridge, MA 02139 United States

Free

Registration by invitation only

Agenda:

Wednesday:
Participants arrive in Cambridge
5:30-7:30 PM, Room 46-3015

Introductions:
Welcoming remarks: Tommy Poggio
Overview: Mandana Sassanfar
Research presentation: Ed Boyden

Thursday:     EDUCATION PROGRAMS – Moderator: Ellen Hildreth

Morning: 9:00 -12:00  in Room 46-3015
-       Overview of the CBMM education program and goals:

  • Ellen Hildreth

-     Curriculum and building bridges between neuroscience and CS within each institution:

  • UPR: Irving Vega
  • UCC: Maria Bykhovskaia
  • CUNY: Susan Epstein
  • Howard: Mohamed Chouikha
  • Wellesley: Mike Wiest

-       CBMM courses and summer course:

  • Ellen Hildreth
  • L. Mahadavan

-       Preparation for graduate and postdoctoral work in intelligence science:

  • Matt Wilson

-       General discussion: Building collaborations on course and curriculum development across institutions.

Afternoon: 1:00 -5:00 – Quantitative Biology Workshop in Room 32-080

Visiting faculty attend Quantitative Biology Workshop session on the use of MATLAB in Neuroscience, to experience a model for future January workshops
https://biology.mit.edu/outreach_initiatives/quantitative_biology_workshop

Evening:  - Networking and discussions

Friday:           RESEARCH PROGRAMS – Moderator: Patrick Winston

Morning: : 9:00 -12:00  in Room 46-3015

-       Overview of CBMM research goals and four thrusts

  • Patrick Winston: Research Overview
  • Gabriel Kreiman: Circuits for Intelligence
  • Boris Katz: Visual Intelligence
  • Nancy Kanwisher: Social Intelligence
  • Josh Tennenbaum: Development of Intelligence

-       Specific research lab overviews

  • Robert Desimone
  • Matt Wilson

-       Research at each partner institution

  • UPR:
  • UCC: Maria Bykhovskaia
  • CUNY: Susan Epstein
  • Howard: Kebreten Manaye, Robert Rwebangira
  • Wellesley: Bevil Conway

-       Discussion of research interests of CBMM and visiting faculty

Afternoon: 1:00 – 5:00

Individual and small-group meetings with MIT/Harvard CBMM faculty in faculty individual offices and labs(exploring synergies for summer sabbaticals, faculty seminars, and students research opportunities)

1:00 -2:00   fMRI demo in Martinos Imaging Center –Room 46-1171)
2:00 -3:00   Microscopy facilities:  Confocal Microscopy on 6th floor
2-photon microscopy on 5th floor

Evening: 5:30 – 7:30                        Networking  and discussion

Saturday Morning: 9:00 -12:00

-     Continue discussion of education and research programs and possible areas of collaboration.

-       Develop concrete plans for future efforts at individual schools and across partner institutions for the advancement of the study of intelligence

-       Goals for years 1, 2, 3 and 4.

Participants:

CBMM Broadening Participation Partners:

Howard University
Kebreten Manaye, Chair, Physiology and Biophysics
Mohamed Chouikha, Chair, Electrical & Computer Engineering
Mugizi (Robert) Rwebangira, Computer Science

CUNY- Hunter College
Susan Epstein, Computer Science
Martin Chodorow , Professor of Psychology and Linguistics
Williams Sakas, Computer Science Department Chair

CUNY- Queens College
Josh Brumberg, Psychology, Director – Brain, Behavior and Cognition Doctoral Programs

University of Puerto Rico at Rio Piedras
Patricia Odonez, Computer Science,
Rafael Arce Nazario  Computer Science Department Chair, rafael.arce@upr.edu
Irving Vega, Prof of Biology and Assistant Dean of Research, irvingvega@gmail.com

Universidad Central del Caribe
Maria Bykhovskaia, Chair, Neuroscience Department

Wellesley College
Ellen Hildreth, Chair, Computer Science Department
Bevil Conway, Neuroscience Program
Mike Wiest, Neuroscience Program

CBMM faculty at MIT and Harvard:

*Tomaso Poggio, Director, CBMM

*Ed Boyden, MIT BCS
*Robert Desimone, MIT BCS
Leslie Kaelbling, MIT Electrical Engineering & Computer Science
*Nancy Kanwisher, MIT BCS
*Boris Katz, MIT Computer Science & Artificial Intelligence Lab
*Gabriel Kreiman, Harvard Medical School
L. Mahadevan, Harvard, Applied Mathematics, Organismic & Evolutionary Biology, and Physics
Ken Nakayama, Harvard Department of Psychology
Rebecca Saxe, MIT Department of Brain & Cognitive Sciences
*Laura Schulz, MIT BCS
Haim Sompolinsky, Harvard Center for Brain Science and Hebrew University
Liz Spelke, Harvard Psychology
*Josh Tenenbaum, MIT BCS
Shimon Ullman, MIT BCS and Weizmann Institute of Science
*Leslie Valiant, Harvard Computer Science and Applied Mathematics
*Matt Wilson, MIT BCS
*Patrick Winston, MIT Electrical Engineering & Computer Science

* Available to meet with visiting faculty during the CBMM Workshop on Broadening Participation in the Science of Intelligence

Organizer:  Mandana Sassanfar

Workshop on Learning Theory, Dec. 18-20, 2014, Montevideo, Uruguay

Dec 18, 2014 - 9:00 am
Workshop on Learning Theory, Dec. 18-20, 2014, Montevideo, Uruguay

December, 18-20, 2014
Montevideo, Uruguay

The workshop is part of the triennial Conference on Foundations of Computational Mathematics (FoCM’14) organized by the Society for Foundations of Computational Mathematics hosted by the Universidad de la Republica in Montevideo, Uruguay.

The goal of the workshop is to investigate the mathematical foundation of learning theory. The meeting will gather experts to discuss current and future challenges in the field.

The workshop is organized by Tomaso Poggio and Lorenzo Rosasco.

Click here to visit event website.

 

Participants

Peter Bartlett (University of California, Berkeley)
Misha Belkin (Ohio State University, Columbus)
Peter Binev (University of South Carolina)
Frédéric Chazal (Institut National de Recherche en Informatique et en Automatique)
Marco Cuturi (Kyoto University)
Franz Kiraly (University College London)
Ankur Moitra (Massachusetts Institute of Technology)
Robert Nowak (University of Wisconsin)
Francesco Orabona (Yahoo! Labs, NY)
Tomaso Poggio (Massachusetts Institute of Technology)
Sasha Rakhlin (University of Pennsylvania, The Wharton School)
Ben Recht (University of California, Berkeley)
Lorenzo Rosasco (MIT, University of Genova and Istituto Italiano di Tecnologia)
Guillermo Sapiro (Duke University)
Ingo Steinwart (Institut für Stochastik und Anwendungen)
Ryota Tomioka ( Toyota Technological Institute at Chicago)
Silvia Villa (Istituto Italiano di Tecnologia, Genova)

Organization

Lorenzo Rosasco
DIBRIS, Università degli Studi di Genova, Italy and
Laboratory for Computational and Statistical Learning
Istituto Italiano di Tecnologia ‒ Massachusetts Institute of Technology
Contact

Videos: Workshop on Learning Data Representation: Hierarchies and Invariance

Nov 22, 2013 - 9:00 am
Venue:  McGovern Institute for Brain Research at MIT (Bldg. 46)

The workshop “Learning Data Representation: Hierarchies and Invariance” was held at the McGovern Institute for Brain Research at MIT (Bldg. 46), from November 22-24, 2013.

The goal of the meeting is to investigate advances and challenges in learning “good representations” from data, in particular representations that can reduce the complexity of later supervised learning stages. The meeting will gather experts in the field to discuss current and future challenges for the theory and applications of learning representations.

This  workshop was organized by Tomaso Poggio and Lorenzo Rosasco and sponsored by the Laboratory for Computational and Statistical Learning (LCSL), joint between the Istituto Italiano di Tecnologia and Massachusetts Institute of Technology and the Center for Brains, Minds and Machines (CBMM).

Read PDF version of workshop’s agenda>

Visit event website for list of participants and detailed agenda>

Speakers have kindly permitted us to share their presentation slides along with videos of most of the talks. Please note a few talks are unavailable due to technical difficulties experienced with the AV equipment during the event.

 

Friday November 22, 2013

Introduction to the workshop

Tomaso Poggio, Director of the Center for Brains, Minds and Machines (CBMM), presented an introduction to CBMM and introduced workshop organizer Dr. Lorenzo Rosasco.

Click here to see slides>

Lorenzo Rosasco (LCSL, MIT) welcomes guests to the Workshop on Learning Data Representation: Hierarchies and Invariance.

 

Session 1: Early Features in Vision

Chair: Carlo Tomasi (Duke U.)

Filters and other potions for early vision and recognition, Pietro Perona (Caltech)
Click here to see slides>

Transformations in early vision from a symmetry argument, Charles Stevens (Salk Institute)
Click here to see slides.

Hierarchical models of the visual cortex, Thomas Serre (Brown U.)
* This video is not available due to technical issues with the recording
Click here to see slides>

Panel discussion: Early Features in Vision
Moderator: Carlo Tomasi (Duke U.)
Panel: William Freeman (MIT CSAIL), Charles Stevens (Salk Institute), Thomas Serre (Brown University), Giulio Sandini (IIT), and Pietro Perona (Caltech.)

Early Features in Vision, Carlo Tomasi (Duke U.)
Click here to see slides>

Eulerian Video Magnification: Engineering Applications of a V1-like Image Representation, Bill Freeman (MIT CSAIL)
 Click here to see slides>

Early Visions and Actions, Giulio Sandini (IIT)
Click here to see slides>

Saturday November 23, 2013

Session 2: Learning Features and Representations

Chair: Alessandro Verri (Università degli Studi di Genova)

Latent structure beyond sparse codes, Benjamin Recht (UC Berkeley)
Click here to see slides>

Dictionary learning: 3+ snippets on learning features, Guillermo Sapiro (Duke U.)
Click here to see slides>

Panel discussion
Moderator: Alessandro Verri (Università degli Studi di Genova)
Panel: Benjamin Recht (UC Berkeley), Lorenzo Rosasco (LCSL, MIT), Misha Belkin (Ohio State), Joachim Buhmann (ETH Zurich), and Guillermo Sapiro (Duke).

Learning Features and representations, Lorenzo Rosasco (LCSL, MIT)
Click here to see slides>

Features and Representations, Misha Belkin (Ohio State U.)
Click here to see slides>

Learning Features and Representations, Joachim Buhmann (ETH Zurich)
Click here to see slides>

Session 3: Learning Invariances and Hierarchies

Chair: James DiCarlo (MIT)

Learning invariant feature hierarchies, Yann LeCun (NYU)
Click here to see slides>

Scattering bricks to build invariants for perception (part 1), Stéphane Mallat (École Polytechnique)

Scattering bricks to build invariants for perception (part 2), Stéphane Mallat (École Polytechnique)
Click here to see slides>

M-theory, Tomaso Poggio (MIT, CBMM)
Click here to see slides>

Panel discussion
Moderator: James DiCarlo (MIT)
Panel: Yann LeCun (NYU), Stéphane Mallat (École Polytechnique), Tomaso Poggio (MIT), Pierre Baldi (U.C.Irvine), and Maximilian Riesenhuber (Georgetown).

Going After Object Recognition to Discover How the Ventral Stream Works, James DiCarlo (MIT)
Click here to see slides>

Learning Invariances and Hierarchies, Pierre Baldi (U.C.Irvine)
Click here to see slides>

Note: Maximilian Riesenhuber (Georgetown) participated in this panel. Unfortunately, the video and slides of his talk are not available.

Sunday November 24, 2013

Session 4: Beyond Feedforward Architectures

Chair: Josh Tenenbaum (MIT, CBMM)

The role of mobility and control in the inference of representations, Stefano Soatto (UCLA)
Click here to see slides>

Atoms of recognition, Shimon Ullman (MIT/Weizmann Inst.)
Click here to see slides>

Compositional models: complexity of representation and inference, Alan Yuille (UCLA)

Panel discussion (video)
Modertor: Josh Tenenbaum (MIT, CBMM)

Panel: Stefano Soatto (UCLA), Shimon Ulllman (MIT/Weizmann Inst.), Alan Yuille (UCLA), and Russ Salakhutdinoff (U. Toronto).

What Makes a Good Representation? From Invariance to Causality, Josh Tenenbaum (MIT, CBMM)

Representation Learning, Russ Salakhutdinov (U. Toronto)
Click here to see slides>

Final remarks, Tomaso Poggio (MIT, CBMM)
Click here to see slides>

Workshop on Learning Data Representation: Hierarchies and Invariance

Nov 22, 2013 - 5:00 am
Workshop on Learning Data Representation: Hierarchies and Invariance
Venue:  MIT: McGovern Institute Singleton Auditorium, 46-3002 Address:  43 Vassar Street MIT Bldg 46 Cambridge, 02139 United States

The goal of the meeting is to investigate advances and challenges in learning “good representations” from data, in particular representations that can reduce the complexity of later supervised learning stages. The meeting will gather experts in the field to discuss current and future challenges for the theory and applications of learning representations.

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

Click here to view Workshop Schedule as a PDF>

Workshop Media:

Videos/slides have been made available online on the workshop webpage.

Presentation slides (kindly made available by all participants) are available on the LSCL Website - links to slides are listed next to the relevant talk description.

Organizer:  Tomaso Poggio Lorenzo Rosasco

Pages

Subscribe to Workshops