[Lisa_teatalk] [Lisa_labo] Tea Talk by Kyle Kastner this Friday 13.30-14.30 @AA3195

Kyle Kastner kastnerkyle at gmail.com
Wed Mar 11 09:27:45 EDT 2015


Definitely! I might even send them beforehand if they are finished early :)

On Wed, Mar 11, 2015 at 8:18 AM, Atousa Torabi <torabi.atousa at gmail.com> wrote:
> Kyle,
>
> Could you please send us your talk slides after your talk?
>
> Thanks,
> Atousa
>
> On Tue, Mar 10, 2015 at 9:21 PM, Kyung Hyun Cho <cho.k.hyun at gmail.com>
> wrote:
>>
>> 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 at 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.
>>>
>>>
>>
>>
>> _______________________________________________
>> Lisa_labo mailing list
>> Lisa_labo at iro.umontreal.ca
>> https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo
>>
>


More information about the Lisa_teatalk mailing list