Date de l'événement : du 15 mai 2014 au 15 septembre 2014

 Le Higgs boson machine learning challenge (HiggsML) sʼest achevé le 15 septembre 2014. Pour la première fois, lʼexpérience ATLAS au CERN a rendu publique une partie des données de simulation utilisées par les physiciens pour optimiser une analyse, en lʼoccurrence lʼanalyse qui a mis en évidence la désintégration du boson de Higgs en paires tau+tau- annoncée en novembre 2013.

The Challenge, hosted by Kaggle, had the all-time record of 1,785 teams participating. Participants had to develop an algorithm that improves the detection of Higgs boson signal events decaying into two tau particles in a sample of simulated ATLAS data that contains few signal and a majority of non-Higgs boson "background" events.

The winner of the four-month long Higgs Machine Learning Challenge, launched on 12 May, 2014 is Gábor Melis from Hungary, followed closely by Tim Salimans from The Netherlands and Pierre Courtiol from France. They receive cash prizes, sponsored by Paris-Saclay Centre for Data Science and Google, of $7000, $4000, and $2000 respectively. 

High Energy Physics (HEP) has been using Machine Learning (ML) techniques such as boosted decision trees (paper) and neural nets since the 90s. These techniques are now routinely used for difficult tasks such as the Higgs boson search. Nevertheless, formal connections between the two research fields are rather scarce, with some exceptions such as the AppStat group at LAL, founded in 2006. In collaboration with INRIA, AppStat  promotes interdisciplinary research on machine learning, computational statistics, and high-energy particle and astroparticle physics.

We are now exploring new ways to improve the cross-fertilization of the two fields by setting up a data challenge, following the footsteps of, among others, the astrophysics community (dark matter and galaxy zoo challenges) and neurobiology (connectomics and decoding the human brain). The organization committee consists of ATLAS physicists and machine learning researchers.

For the Challenge however, no knowledge of particle physics was required but skills in machine learning -- the training of computers to recognize patterns in data – was at stake. 

"The Higgs Machine Learning challenge was special. It shows that machine learning and data mining are very important to the world, not just in generating profit but also in cutting-edge research. In the course of the Challenge, I learned that physicists and computer scientists think in different ways. Combining their strengths might lead to better results," says Crowwork's Tong He, a Masters student in Data Mining and Bioinformatics at Simon Fraser University, Canada.

"The Challenge is done but we are only really half-way through the project. We now have to digest the many ideas submitted by the participants, and establish long-term collaboration between high energy physics and machine learning communities," says David Rousseau, ATLAS physicist and organizer of the Challenge. 


Read Atlas news on this link.