
There will be a presentation on the Research Thrust 5 “Theories for Intelligence.”
T. Poggio:
Thrust 5: Theory is the common language between thrusts but it is not a goal in itself. The CBMM challenge question what is there and m-theory
- Theory: Invariances reduce sample complexity
- Algorithm: how the ventral stream may learn/compute invariant features
Speakers:
- Qianli Liao – Computational test: algorithm performs well in face verification
- Joel Leibo – Neuroscience test: algorithm is consistent with physiology of face cells
- Leslie Valiant – The neuroidal model: modeling how neural circuits are cumulatively learned
Details
Date:
November 8, 2013
Time:
4:30 pm to 6:00 pm
Venue:
Harvard University: Northwest Bldg, Room 243Address:
52 Oxford Street
Harvard University Northwest Building
Cambridge, 02138