Towards a theory of layered neural circuit architectures
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Daniel McNamee.
A main challenge in neuroscience is finding a general computational principle that explains why cortical circuits are organized in particular structures. I will start out with the optimal storage principle as a guideline to derive optimal neural architecture. For optimal storage, one needs to have the maximal capacity of a neural network and a learning rule to achieve the capacity. For conventional recurrent neural networks, the maximal capacity is known as the Gardner bound, and this bound is achieved via the Three-Threshold Learning Rule (3TLR). However, calculating the storage capacity of hierarchical neural circuits has been problematic. I will present my recent results suggesting that the capacity of an expansive autoencoder increases superlinearly with the expansion ratio using simulations and Gardner’s replica theory. I will discuss some of the theoretical challenges and limitations of these networks.
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)
Alireza Alemi (École Normale Supérieure)
Tuesday 31 May 2016, 11:30-12:30