Skip to content. | Skip to navigation

Personal tools

Navigation

You are here: Home

Deep Learning, Tools and Methods workshop (July 4-5-6, 2016)

Idiap logo

The objective of this workshop was to present the current available software and hardware solutions for deep machine learning. We focused on the two main industrial frameworks for the task: Facebook's Torch and Google's TensorFlow, and discussed the general principles of deep learning, best practices, "under the hood" mechanisms, and the existing hardware solutions to deal with the specific computational requirements of these methods.

All the talks have been recorded, and individual links to webcasts and slides are provided in the program below.

For more information please contact Fran├žois Fleuret.

Program

Monday 04.07 Tuesday 05.07 Wednesday 06.07
10:00-11:00 S. Chintala
(Facebook)
Torch 1
webcast | slides
M. Rosca
(Google)
TensorFlow 1
webcast
11:00-11:15 Coffee break Coffee break
11:15-12:15 S. Chintala
(Facebook)
Torch 2
webcast | slides
M. Rosca
(Google)
TensorFlow 2
webcast
12:15-14:00 Lunch Lunch
14:00-15:00 Y. Bengio
(UMontreal)
Deep Supervised Learning of Representations
webcast | slides
Y. Bengio
(UMontreal)
Deep Generative Models
webcast | slides
M. Breternitz
(AMD)
AMD's Open Compute and Open Source cross platform solutions for Machine Learning
webcast | slides
15:00-15:15 Coffee break Coffee break Coffee break
15:15-16:15 A. Lowndes
(NVIDIA)
Hardware & software update from NVIDIA, Enabling Deep Learning
webcast | slides
S. Chintala
(Facebook)
Torch 3
webcast | slides
M. Rosca
(Google)
TensorFlow 3
webcast
16:15-17:15 Q&As
webcast
Q&As
webcast
Q&As
webcast


Post-event poll

The event was attended by more than 250 persons every day, and the respondents to the poll following the event rated it in large majority good (47%) or very good (43.9%). The attendees span a wide range of origins, from the academic to the private sector, across Switzerland and Europe.

Gender
82.1%Male
17.8%Female
Employment
44.4%PhD student
28.9%Academic (non-student)
16.5%Industry / private sector
Institution of origin
35.0%EPFL
17.2%Idiap research institute
13.5%Private sector
12.7%Swiss universities
7.0%HES
6.4%Foreign universities
3.4%ETHZ
2.7%CREM/CSEM/CHUV

With the support of

SNSF logo Haslerstiftung logo

TheArk logo Ideark logo Klewel logo

City of Martigny logo Canton of Valais logo