Capacity and errors in classification of object manifolds
Add to your list(s)
Download to your calendar using vCal
 Uri Cohen (Hebrew University of Jerusalem) Thursday 03 June 2021, 10:00-11:15 Online on Zoom.
If you have a question about this talk, please contact Yul Kang.
What makes a good object representation? How do object representations change along biological or artificial hierarchies? I will introduce a measure called classification capacity and argue it quantifies the goodness of a neural representation with respect to manifold classification. A theoretical analysis using tools from statistical physics relates this capacity to the geometry of object manifolds, thus augmenting the computational definition with an intuitive geometric perspective. For artificial hierarchies, theory was used to describe changes in representation along deep convolutional neural networks. For noisy biological hierarchies, relating capacity to generalization error with respect to neural noise allows one to correctly interpret experimental results.
Join via Zoom:
https://us02web.zoom.us/j/84958321096?pwd=dFpsYnpJYWVNeHlJbEFKbW1OTzFiQT09
Meeting ID: 849 5832 1096
Passcode: 506576
This talk is part of the Computational Neuroscience series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|
![[Search]](http://talks.cam.ac.uk/images/search.gif?1209136071)
|![[A-Z Index]](http://talks.cam.ac.uk/images/az.gif?1209136071)
|![[Contact]](http://talks.cam.ac.uk/images/contact.gif?1209136071)
![[University of Cambridge]](http://talks.cam.ac.uk/images/identifier2.gif?1209136071){kind=small}
![[Talks.cam]](http://talks.cam.ac.uk/images/talkslogosmall.gif?1209136071)
