Fall 2011
Class Times: Friday 11:00-2:00 pm Units: 3-0-9 Location: 46-5193 Instructors: Shimon Ullman and Tomaso Poggio Office Hours: TBA Email Contact : sullman@mit.edu
Announcements
9/23/2011: Tentative final presentation dates: 11/8 and 11/22 at 5:30 pm.
9/16/2011: If you would like to be on the class mailing list, please send an email to olewis@mit.edu with "mailing list" in the subject line.
Class projects: The selection of a project topic is pretty free. A good choice will be to use one of the questions raised by speakers during class. Another possibility is to write a critical review of the literature related to a problem covered in class. Such a review should summarize the state of the art in the literature, and add your own criticism and evaluation. A typical length of the project is around 5-8 pages. Students who need a grade soon for this class should submit the written project within 2 weeks from the last day of class. For any question, or if you want to discuss a possible project topic, send e-mail to shimon.ullman@gmail.com
Course description
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?
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. Lectures will be complemented with readings, discussion, and individual or group projects.
Prerequisites
The course is open to all graduate students; undergraduates can take the course with instructor permission.
Grading
Grading will be based on participation and a final project.
Schedule
Date Title Instructor(s) Class 01 Fri 09 Sep Learning Theory Tomaso Poggio and Lorenzo Rosasco Class 02 Fri 16 Sep Neural Circuits Michale Fee Class 03 Fri 23 Sep Bayesian Approaches to Cognition Josh Tenenbaum Class 04 Fri 30 Sep Language Edward Gibson and Tim O'Donnell Class 05 Fri 07 Oct Cognitive Development and the Evolution of Behavior Laura Schulz and Andrew Lo Class 06 Fri 14 Oct Learned and Innate Strcutures in Categorization Shimon Ullman Class 07 Fri 21 Oct Planning and Motor Control Matthew Wilson and Russ Tedrake Class 08 Fri 28 Oct Evolutionary Games and Social Cognition Martin Nowak and Rebecca Saxe Class 09 Fri 04 Nov General and Domain Specific Structures and Nature vs. Nurture Nancy Kanwisher and Mriganka Sur Veteran's day - no class Class 10 Fri 18 Nov Social and Collective Intelligence Thomas Malone and Sandy Pentland Thanksgiving - no class Class 11 Fri 02 Dec Computers and Games David Silver Class 12 Fri 09 Dec Perception and Language, and Stories Patrick Winston and Boris Katz