New Machine Learning Developments in ROOT/TMVA

Document identifier: oai:DiVA.org:ltu-76550
Access full text here:10.1051/epjconf/201921406014
Keyword: Natural Sciences, Computer and Information Sciences, Software Engineering, Naturvetenskap, Data- och informationsvetenskap, Programvaruteknik, Computer Sciences, Datavetenskap (datalogi), ROOT, TMVA, Machine Learning, Maskininlärning
Publication year: 2019
Abstract:

The Toolkit for Multivariate Analysis, TMVA, the machine learning package integrated into the ROOT data analysis framework, has recently seen improvements to its deep learning module, parallelisation of multivariate methods and cross validation. Performance benchmarks on datasets from high-energy physics are presented with a particular focus on the new deep learning module which contains robust fully-connected, convolutional and recurrent deep neural networks implemented on CPU and GPU architectures. Both dense and convo-lutional layers are shown to be competitive on small-scale networks suitable for high-level physics analyses in both training and in single-event evaluation. Par-allelisation efforts show an asymptotical 3-fold reduction in boosted decision tree training time while the cross validation implementation shows significant speed up with parallel fold evaluation.

Authors

Kim Albertsson

Luleå tekniska universitet; EISLAB; CERN
Other publications >>

Sergei Gleyze

University of Florida
Other publications >>

Marc Huwiler

EPFL
Other publications >>

Vladimir Ilievski

EPFL
Other publications >>

Lorenzo Moneta

CERN
Other publications >>

Saurav Shekar

ETH Zurich
Other publications >>

Victor Estrade

CERN
Other publications >>

Akshay Vashistha

CERN. Karlsruhe Institute of Technology
Other publications >>

Stefan Wunsch

CERN. Karlsruhe Institute of Technology
Other publications >>

Omar Andres Zapata Mesa

University of Antioquia. Metropolitan Institute of Technology
Other publications >>

Record metadata

Click to view metadata