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 KasterDate/Time: 13 Apr (Friday) @13.30Place: AA3195Title: Theano + Caffe, with a side of GoogLeNet, in sklearn-theanoAbstract:sklearn-theano (http://sklearn-theano.github.io/) is a package forapplying pretrained neural networks to data using python, numpy andtheano. sklearn-theano strives to conform to the scikit-learninterface, and can be flexibly added into machine learning pipelinesas an upfront transform followed by standard classifiers andtransformers from scikit-learn. Many of the models in sklearn-theanoalso work as standalone classifiers and object localizers.We have recently added support for a potentially huge number ofpretrained models by adding a bridge between Theano and Caffe. Thistalk will go over some interesting notes about the architecture ofGoogLeNet itself, the key things necessary to bring *new* models intosklearn-theano (or theano in general), and some discussion about wherewe plan to go next.