10-15 March 2019
Steinmatte conference center
Europe/Zurich timezone

PhenoAI and iDarkSurvey: Learning (from) high-dimensional models

Not scheduled
Steinmatte conference center

Steinmatte conference center

Hotel Allalin, Saas Fee, Switzerland https://allalin.ch/conference/
Oral Track 2: Data Analysis - Algorithms and Tools Track 2: Data Analysis - Algorithms and Tools


Sydney Otten (Radboud Universiteit Nijmegen)


Although the standard model of particle physics is successful in describing physics as we know it, it is known to be incomplete. Many models have been developed to extend the standard model, none of which have been experimentally verified. One of the main hurdles in this effort is the dimensionality of these models, yielding problems in analysing, visualising and communicating results. Because of this, most current day analyses are done using simplified models, but in this process descriptive power is lost. However, by using machine learning on simulated model points, we show that we can overcome these problems and predict both binary exclusion an continuous likelihood in any parameter space. This functionality is implemented in the PhenoAI framework, allowing non-expert users of machine learning to use trained machine learning models in their own analyses. The simulated data can be stored in our new webbased database and model visualisation tool iDarkSurvey.

Primary authors

Mr Jisk Attema (Netherlands eScience center) Sascha Caron (Nikhef National institute for subatomic physics (NL)) Mr Faruk Diblen (Netherlands eScience center) Mr Tom Heskes (Radboud University Nijmegen) Sydney Otten (Radboud Universiteit Nijmegen) Krzysztof Rolbiecki (University of Warsaw) Roberto Ruiz De Austri (Instituto de Fisica Corpuscular (ES)) Jong Soo Kim Mr Bob Stienen (Radboud University Nijmegen)

Presentation materials

There are no materials yet.