Embed code
Note: this content has been automatically generated.
uh_huh uh_huh how easy
how easy is it actually for positions to interpret the
the the results that they're getting 'cause they're getting like feature maps and things like that that that
nontrivial i would say to actually interpreting right right so
it's perfectly true that when we are here
what they get is is just the five so that it's not very sexy actively so uh
what they need to do is to to be like a uh well advanced in statistic it at our which will
conduct also okay with that but we need to extract like a regression since things like that's based on this
on this is just the five so i would say for now it's it's not easy to interpret
especially with extra features that easy what we are now willing to do is to include a little bit
more machine learning in this but from here to extract some score so that at least they
can the computer or c. values and things like that so they can really have to interpret the
performance of these result going through a a statistical software but this is that you can issue

Share this talk: 


Conference program

Welcome
Sébastien Marcel, Senior Researcher, IDIAP, Director of the Swiss Center for Biometrics Research and Testing
24 March 2017 · 9:17 a.m.
Keynote - Reproducibility and Open Science @ EPFL
Pierre Vandergheynst, EPFL VP for Education
24 March 2017 · 9:20 a.m.
Q&A: Keynote - Reproducibility and Open Science @ EPFL
Pierre Vandergheynst, EPFL VP for Education
24 March 2017 · 9:54 a.m.
VISCERAL and Evaluation-as-a-Service
Henning Müller, prof. HES-SO Valais-Wallis (unité e-health)
24 March 2017 · 11:35 a.m.
Q&A - VISCERAL and Evaluation-as-a-Service
Henning Müller, prof. HES-SO Valais-Wallis (unité e-health)
24 March 2017 · 12:07 p.m.

Recommended talks

Discussion avec Martin Dougiamas
Martin Dougiamas, Fondateur et développeur en chef de MOODLE
8 July 2016 · 3:46 p.m.