Player is loading...

Embed

Embed code

Transcriptions

Note: this content has been automatically generated.
00:00:00
yeah
00:00:05
oh yes yeah we agree on most of the time targeting online the on on on my processing application
00:00:14
uh and most frequently we need to to have both the the and then i i'm not rises on control aspect
00:00:21
so for this reason rees on it it needs to be a also like plus plus is seen
00:00:25
most of the time means beings be very fast switch one of the constraining the that we have
00:00:30
one four the court what aspect it means sometimes really
00:00:33
uh i frame rate so sometimes can be up to uh
00:00:37
up to a control at at at uh we're up to one thousand healthful
00:00:42
one inch me so don't we need to provide a a signal cool about
00:00:48
oh
00:00:52
so i want to um i didn't show value in the time to show value but compared to a vector position of the word signal
00:00:59
uh it it's still much less parameter else because of this crank one structure are a way
00:01:07
we need to learn wait upon it tells a lot but are in um which
00:01:12
moral dimension and if you would like to highs uh all uh all of data

Share this talk: 


Conference Program

Methods for Rule and Knowledge Extraction from Deep Neural Networks
Keynote speech: Prof. Pena Carlos Andrés, HEIG-VD
3 May 2019 · 9:10 a.m.
349 views
Q&A - Keynote speech: Prof. Pena Carlos Andrés
Keynote speech: Prof. Pena Carlos Andrés, HEIG-VD
3 May 2019 · 10:08 a.m.
Visualizing and understanding raw speech modeling with convolutional neural networks
Hannah Muckenhirn, Idiap Research Institute
3 May 2019 · 10:15 a.m.
Q&A - Hannah Muckenhirn
Hannah Muckenhirn, Idiap Research Institute
3 May 2019 · 10:28 a.m.
Concept Measures to Explain Deep Learning Predictions in Medical Imaging
Mara Graziani, HES-SO Valais-Wallis
3 May 2019 · 10:32 a.m.
What do neural network saliency maps encode?
Suraj Srinivas, Idiap Research Institute
3 May 2019 · 10:53 a.m.
Transparency of rotation-equivariant CNNs via local geometric priors
Dr Vincent Andrearczyk, HES-SO Valais-Wallis
3 May 2019 · 11:30 a.m.
Q&A - Dr Vincent Andrearczyk
Dr Vincent Andrearczyk, HES-SO Valais-Wallis
3 May 2019 · 11:48 a.m.
Interpretable models of robot motion learned from few demonstrations
Dr Sylvain Calinon, Idiap Research Institute
3 May 2019 · 11:50 a.m.
Q&A - Sylvain Calinon
Dr Sylvain Calinon, Idiap Research Institute
3 May 2019 · 12:06 p.m.
The HyperBagGraph DataEdron: An Enriched Browsing Experience of Scientific Publication Databa
Xavier Ouvrard, University of Geneva / CERN
3 May 2019 · 12:08 p.m.
Improving robustness to build more interpretable classifiers
Seyed Moosavi, Signal Processing Laboratory 4 (LTS4), EPFL
3 May 2019 · 12:21 p.m.
Q&A - Seyed Moosavi
Seyed Moosavi, Signal Processing Laboratory 4 (LTS4), EPFL
3 May 2019 · 12:34 p.m.