NOTE: the course temporally lost its "W" flag. It will get it back by petition on the first day of class.
One of our major scientific challenges of the century is to understand the functioning of the human brain. Computational models play a vital role in a complete picture of brain function, particularly at modeling more macroscopic structures that more directly relate to our everyday behavior. The goal of this course is to describe computational models of intelligent behavior and how they relate to structures in the brain.
Students should have a mathematical background sufficient to grasp the ideas behind learning algorithms. This would include calculus and some linear algebra.
Instructor: Dana H. Ballard
TA: Craig Corcoran
Textbook: Brain Computation as Hierarchical Abstraction, MITPress 2015(Feb)
Discussions: Piazza page
Students will write five short evaluations of scientific papers in computational brain science. Students will also review one popular science book in the area.
In addition one group lab experiment will be done and its outcomes written up in a report and presented orally.
Including a group lab report, a total of seven papers will be required, each of 1-2 pages in length. Papers must be submitted electronically in Word format using the turnin command.
The book to be evaluated is:
The text for the course will be notes written by the instructor. Electronic access for these will be given at the first day of class.
Example papers from the literature:
Negative: "Betting your life on an algorithm" Dennett
Positive:Koch & Poggio