As a related note, I think it is also possible to learn parse trees (hence the tree data structure) using reinforcement learning for images and natural language,For images:For natural language processing, I think Hal Daume published a few papers with imitation learning.But these examples are not using neural networks.--On Thu, Jan 16, 2014 at 2:09 PM, Yoshua Bengio <yoshua.bengio@gmail.com> wrote:
Here is the paper I mentioned during Ian's presentation about training a recurrent net to exploit a push-pop stack:It was not Mike Mozer but Lee Giles.-- YoshuaOn Mon, Jan 13, 2014 at 1:04 PM, Razvan Pascanu <r.pascanu@gmail.com> wrote:
_______________________________________________Hi all,First of all the schedule has changed, and tea talks will be Wednesdays from 13-14 from now on.
There is an exception this week. We will have Ian presenting this **Thursday from 13:00 to 14:00**.Speaker: Ian GoodfellowTitle: Ian's ideas for research projectsAbstract:
I'll throw out a few of my recent ideas for research
projects, ranging from easy to idealistic:
-Restricted maxout units
-Regularizing piecewise linear nets to change pieces rarely
-Sparsely connected recurrent nets
-Trajectory optimization for recurrent nets
-"Cognitive agency" and how you can use it to do things like
discrete-state nets, dynamically structured nets, and nets that
interact with data structures like stacks and tapesI hope to see many of you there. And please register for giving tea talks.
Razvan
Lisa_labo mailing list
Lisa_labo@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo
_______________________________________________
Lisa_labo mailing list
Lisa_labo@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo
Caglar GULCEHRE
_______________________________________________
Lisa_labo mailing list
Lisa_labo@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo