Class Times: Friday 11:00-2:00 pm Units: 3-0-9 Location: 46-5193 Instructors: Shimon Ullman and Tomaso Poggio (TA Alessandro Rudi) Office Hours: TBA Email Contact : email@example.com Previous Class: FALL 2011
9/07/2012: Only today the class will be in room 46-5193
10/05/2012: From now on the class will be in room 46-5193
Class projects: The final assignment is a short paper, about 5 pages or so. It needs to be related to the study of intelligence, but other than that it's open. It can take one of several forms.
- First, it can be a topic that interests you, and can be related to your research. If you have a suggested topic, send me (Shimon Ullman) an e-mail with a short description, and I'll be glad to give feedback.
- A second option is to read a number of papers on a selected topic that you found interesting. If you have a preference, again you can e-mail to me and I can help with papers selection. The project should then be a summary of the papers (about 3 pages), and then a critique and suggestions for future studies (about 2 pages).
- Third, this web site has a couple of suggestions of topics with a selection of papers to read. You can select on of this group of papers and write a project paper summarizing and commenting on these papers.
- Deep Learning. References:
 Hinton G. E. Learning multiple layers of representation. TRENDS in Cognitive Sciences Vol.11 No.10
 Mohamed A., Dahl G., and Hinton G. Deep Belief Networks for phone recognition NIPS '09
 Markoff J Scientists see promise in Deep Learning Program. New York Times
 Le Q. V., Ranzato M. A., et al. Building High-level Features Using Large Scale Unsupervised Learning ICML '12
- Development: learning and innate. References:
 Hamlin J., Wynn K. and Bloom P. Social evaluation by preverbal infants Nature Letters Vol.450, 22 November 2007
 Meltzoff A. N. and Moore N. K. Imitation of Facial and Manual Gestures by Human Neonates Science Vol.198, No. 4312
 Damme R. V., Wilson R. S., et al. Rational imitation in preverbal infants Nature Comm. Vol.415, Feb. 14 2002
 Tenenbaum J. B., et al. How to Grow a Mind: Statistics, Structure, and Abstraction Science Vol.331, Mar. 11 2011
 Kinzler K. D. and Spelke E. S. Core systems in human cognition Progress in Brain Research, Vol. 164
 Woodward A. L. Infants' Grasp of Others' Intentions Current Directions in Psychological Sciences Vol.18 N.1
The problem of intelligence – its nature, how it is produced by the brain and how it could be replicated in machines – is a deep and fundamental problem that cuts across multiple scientific disciplines. Philosophers have studied intelligence for centuries, but it is only in the last several decades that developments in a broad range of science and engineering fields have opened up a thriving "intelligence research" enterprise, making questions such as these approachable: How does the mind processes sensory information to produce intelligent behavior, and how can we design intelligent computer algorithms that behave similarly? What is the structure and form of human knowledge – how is it stored, represented and organized? How do human minds arise through processes of evolution, development and learning, and what are their roots in genetics? How does collective intelligence arise in social and economic systems? How are cognitive domains including language, perception, social cognition, planning and motor control combined and integrated? Are there common principles of learning, prediction, decision or planning that span across different domains?
The second iteration of this course will explore these issues with an approach that involves the integration of the fields of cognitive science, which studies the mind, neuroscience, which studies the brain, and computer science and artificial intelligence, which develop intelligent hardware and software. Each week, different faculty members will lecture on a research topic that relates to the problem of intelligence. This year speakers will complement last year's lectures. The class will also consist of readings, discussion, and individual or group projects.
The course is open to all graduate students; undergraduates can take the course with instructor permission.
Grading will be based on participation and a final project.
Date Title Instructor(s) Class 01 Fri 07 Sep Lines, shading, and 3D Shape Edward H. Adelson Class 02 Fri 14 Sep Planning and action in complex domains Leslie Pack Kaelbling Fri 21 Sep No Class Class 03 Fri 28 Sep Vladimir Vapnik - Lorenzo Rosasco - Tomaso Poggio Class 04 Fri 05 Oct A Regularization Tour of Machine Learning Lorenzo Rosasco - Tomaso Poggio Class 05 Fri 12 Oct Statistical processing in early vision Ruth Rosenholtz Class 06 Fri 19 Oct Early stages in the development of visual intelligence Pawan Sinha Class 07 Fri 26 Oct James DiCarlo Class 08 Fri 02 Nov Technologies for Analyzing How Brain Circuits Generate Intelligence Edward Boyden Class 09 Fri 9 Nov Object recognition and attention Robert Desimone Class 10 Fri 16 Nov Drazen Prelec Fri 23 Nov No Class Class 11 Fri 30 Nov Shimon Ullman Class 12 Fri 7 Dec The computational magic of the ventral stream: sketch of a theory Shimon Ullman - Tomaso Poggio