Computational Models of the Neocortex

.
Announcements
- Projects are due 5 PM on December 15.
- Video and slides from Prof. Dean's talk available (also linked from Supplementary Materials page).


Menu
Reading and Presentations Schedule
References
Supplementary Materials
Project Notes


Instructor:
Thomas Dean

Time:
Mondays and Wednesdays 3:15-4:30

Place:
Gates 100 (on Oct. 23 only, in Bldg. 420 Room 371)

Description:
The problem of modeling the primate perceptual neocortex using probabilistic graphical models, including Bayesian and Markov networks, and extensions to model time and change such as hidden Markov models and dynamic Bayesian networks. Problems of learning, inference, and attention. Sources include literature in computational and cognitive neuroscience, machine learning, and other fields that bear on how biological and engineered systems make sense of the world. Prerequisites: basic probability theory, algorithms, and statistics.