Dear all,
Again, sorry about the mistake in the email body. It's "March" not "April". I apologize.
To those who asked me about the potential change of time to 14.00: unfortunately, it's not possible, as there will be another event at the same place starting at 15.00.
Best, - K
On Tue, Mar 10, 2015 at 6:39 AM, Kyung Hyun Cho cho.k.hyun@gmail.com wrote:
Dear all,
Last year Kyle told us about sklearn-theano which can be used to bridge between scikit-learn and Theano. Now, he's ready to tell us how we can even bridge Theano with Caffe (!) In other words, we can use GoogLeNet easily together with Theano now. Isn't it awesome? Furthermore, it's going to be the thirteenth this Friday (huh?)
The talk will be on Friday at 13.30 in the usual place AA3195. See below for the details.
- Cho
=== Speaker: Kyle Kaster Date/Time: 13 Apr (Friday) @13.30 Place: AA3195 Title: Theano + Caffe, with a side of GoogLeNet, in sklearn-theano Abstract: sklearn-theano (http://sklearn-theano.github.io/) is a package for applying pretrained neural networks to data using python, numpy and theano. sklearn-theano strives to conform to the scikit-learn interface, and can be flexibly added into machine learning pipelines as an upfront transform followed by standard classifiers and transformers from scikit-learn. Many of the models in sklearn-theano also work as standalone classifiers and object localizers.
We have recently added support for a potentially huge number of pretrained models by adding a bridge between Theano and Caffe. This talk will go over some interesting notes about the architecture of GoogLeNet itself, the key things necessary to bring *new* models into sklearn-theano (or theano in general), and some discussion about where we plan to go next.