Weekly Research Meetings

CBMM Research Meeting: Babies and AI: What can the fields of cognitive development and machine intelligence learn from each other?

Oct 20, 2017 - 4:00 pm
Alison Gopnik
Venue:  MIT 46-5165 (MIBR Reading Room) Speaker/s:  Alison Gopnik, University of California at Berkeley

Abstract: Gopnik will speak for 20-30 minutes about how the study of cognitive development in babies and older children can inform the development of AI systems, and also how ideas from engineering might further our understanding of cognitive development across the lifespan. This short talk will be the trigger for a broader discussion about these issues, which we hope many CBMM faculty, postdocs and students will participate in.

Speaker Bio:  Alison Gopnik is a professor of psychology and affiliate professor of philosophy at the University of California at Berkeley. She received her BA from McGill University and her PhD. from Oxford University. She is an internationally recognized leader in the study of children’s learning and development and was one of the founders of the field of “theory of mind”, an originator of the “theory theory” of children’s development and more recently introduced the idea that probabilistic models and Bayesian inference could be applied to children’s learning. She has held a Center for Advanced Studies in the Behavioral Sciences Fellowship, the Moore Distinguished Scholar fellowship at the California Institute of Technology, the All Souls College Distinguished Visiting Fellowship at Oxford, and King’s College Distinguished Visiting Fellowship at Cambridge. She is an elected member of the Society of Experimental Psychologists and the American Academy of Arts and Sciences and a fellow of the Cognitive Science Society. She has been continuously supported by the NSF and was PI on a 2.5 million dollar interdisciplinary collaborative grant on causal learning from the McDonnell Foundation.

She is the author or coauthor of over 100 journal articles and several books including “Words, thoughts and theories” MIT Press, 1997, and the bestselling and critically acclaimed popular books  “The Scientist in the Crib” William Morrow, 1999, “The Philosophical Baby; What children’s minds tell us about love, truth and the meaning of life”, and “The Gardener and the Carpenter”, Farrar, Strauss and Giroux, the latter two won the Cognitive Development Society Best Book Prize in
2009 and 2016). She has also written widely about cognitive science and psychology for Science, The New York Times, Scientific American, The Atlantic, The New Yorker, The Times Literary Supplement, The New York Review of Books, New Scientist and Slate, among others. Her TED talk on her work has been viewed more than 2.9 million times. And she has frequently appeared on TV and radio including “The Charlie Rose Show” and “The Colbert Report”. Since 2013 she has written the Mind and Matter column for the Wall Street Journal.

Organizer:  Joel Oller Organizer Email:  cbmm-contact@mit.edu

CBMM Research Meeting: Towards Understandable Deep Networks for Vision

Oct 13, 2017 - 4:00 pm
Photo of Prof. Alan Yuille
Venue:  McGovern Reading Room (46-5165) Address:  43 Vassar Street, Cambridge, MA 02139 Speaker/s:  Prof. Alan Yuille, John Hopkins University

Abstract: This talk will update progress on a research program which was presented in “Deep Networks and Beyond” at the CBMM AI workshop at Stanford. The goal is to develop hierarchical architectures with the same strong performance abilities as deep networks but which are also able to model the flexibility and adaptiveness of biological visual systems. These architectures are intended to be simpler and more explainable, require little supervision and few training examples, and to be adaptive to situations/environments which they have not encountered. In particular, we give new results for unsupervised learning of objects and object viewpoints, one- and few-shot learning for discriminative tasks, and the ability to deal with adversarial attacks. We conclude by speculating on how vision algorithms should be evaluated given the increasingly complexity of visual tasks and the impracticality of getting sufficient data for training and testing.

Organizer:  Joel Oller Organizer Email:  cbmm-contact@mit.edu

CBMM next phase: 4 modules

Oct 6, 2017 - 4:00 pm
Venue:  MIT Building 46-3002 (Singleton Auditorium) Speaker/s:  CBMM PIs

We will introduce the 4 proposed modules for CBMM's renewal. CBMM PIs will present and discuss their research plans and goals at CBMM for the next 5 years. The talks session will be followed by a reception/party (6pm-8pm) to celebrate the renewal by NSF.

Contact for details: Guy Ben-Yosef, gby@mit.edu

Organizer:  Joel Oller Organizer Email:  cbmm-contact@mit.edu

CBMM Research Meeting: Language and Evolution

May 30, 2017 - 4:00 pm
Venue:  McGovern Seminar Room 46 -3189 Address:  43 Vassar St, Cambridge, MA 02139 Speaker/s:  Noam Chomsky (MIT)  

Title: Language and Evolution

In their latest book, Why Only Us: Language and Evolution, Berwick and Chomsky discuss the biolinguistic perspective on language, which views language as a particular object of the biological world; the computational efficiency of language as a system of thought and understanding; the tension between Darwin’s idea of gradual change and our contemporary understanding about evolutionary change and language; and evidence from nonhuman animals, in particular vocal learning in songbirds.

Organizer:  Georgios Evangelopoulos Gadi Geiger Organizer Email:  gevang@mit.edu

CBMM Research Meeting: Parsing Humans with Comp

Oct 21, 2016 - 4:00 pm
Photo of Alan Yuille
Venue:  Northwest Science Building, Room 243, Harvard University Speaker/s:  Alan Yuille (CBMM, Johns Hopkins University)

Abstract: This talk describes work on detecting and parsing humans into joints and semantic parts. It combines deep networks with graphical models for reasoning about the spatial relations between joints. We discuss methods for dealing with occlusion and scale variations. Finally we describe compositional methods for extracting key-point motifs for classifying human actions.

Learning about AI by playing video games

Oct 7, 2016 - 4:00 pm
Venue:  McGovern Institute for Brain Research, MIT Bldg. 46 Room 5165 Address:  43 Vassar St, Cambridge MA 02139 Speaker/s:  Pedro Tsividis and Josh Tenenbaum 

NOTE - *Please bring a laptop, as this will be a participatory session. We will actually be playing video games for much of it. We encourage everyone to bring their laptop and actively participate.*

CBMM Research Meeting

Sep 16, 2016 - 4:00 pm
Venue:  MIT Building 46, Room 3189 Address:  43 Vassar St, Cambridge MA 02139 Speaker/s:  Tomaso Poggio

Topic: CBMM state and updates  

- State of CBMM (Tomaso Poggio)

- BMM summer school recap (Gemma Roig)

- Engineering of Intelligence Teams (Greg Hale)

- Technology and resources for CBMM (Kris Brewer)

- NSF renewal proposal updates (Kathleen Sullivan)

- Upcoming meetings

Pages

Subscribe to Weekly Research Meetings