Cargando…
Fast Inference for Machine Learning in ROOT/TMVA
ROOT provides, through TMVA, machine learning tools for data analysis at HEP experiments and beyond. However, with the rapidly evolving ecosystem for machine learning, the focus of TMVA is shifting. We present the new developments and strategy of TMVA, which will allow the analyst to integrate seaml...
Autores principales: | , , , , |
---|---|
Lenguaje: | eng |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | https://dx.doi.org/10.1051/epjconf/202024506008 http://cds.cern.ch/record/2752851 |
_version_ | 1780969332296122368 |
---|---|
author | Albertsson, Kim An, Sitong Moneta, Lorenzo Wunsch, Stefan Zampieri, Luca |
author_facet | Albertsson, Kim An, Sitong Moneta, Lorenzo Wunsch, Stefan Zampieri, Luca |
author_sort | Albertsson, Kim |
collection | CERN |
description | ROOT provides, through TMVA, machine learning tools for data analysis at HEP experiments and beyond. However, with the rapidly evolving ecosystem for machine learning, the focus of TMVA is shifting. We present the new developments and strategy of TMVA, which will allow the analyst to integrate seamlessly, and effectively, different workflows in the diversified machine-learning landscape. Focus is put on a fast machine learning inference system, which will enable analysts to deploy their machine learning models rapidly on large scale datasets. We present the technical details of a fast inference system for decision tree algorithms, included in the next ROOT release (6.20). We further present development status and proposal for a fast inference interface and code generator for ONNX-based Deep Learning models. |
id | oai-inspirehep.net-1832184 |
institution | Organización Europea para la Investigación Nuclear |
language | eng |
publishDate | 2020 |
record_format | invenio |
spelling | oai-inspirehep.net-18321842021-03-01T08:02:34Zdoi:10.1051/epjconf/202024506008http://cds.cern.ch/record/2752851engAlbertsson, KimAn, SitongMoneta, LorenzoWunsch, StefanZampieri, LucaFast Inference for Machine Learning in ROOT/TMVAComputing and ComputersROOT provides, through TMVA, machine learning tools for data analysis at HEP experiments and beyond. However, with the rapidly evolving ecosystem for machine learning, the focus of TMVA is shifting. We present the new developments and strategy of TMVA, which will allow the analyst to integrate seamlessly, and effectively, different workflows in the diversified machine-learning landscape. Focus is put on a fast machine learning inference system, which will enable analysts to deploy their machine learning models rapidly on large scale datasets. We present the technical details of a fast inference system for decision tree algorithms, included in the next ROOT release (6.20). We further present development status and proposal for a fast inference interface and code generator for ONNX-based Deep Learning models.oai:inspirehep.net:18321842020 |
spellingShingle | Computing and Computers Albertsson, Kim An, Sitong Moneta, Lorenzo Wunsch, Stefan Zampieri, Luca Fast Inference for Machine Learning in ROOT/TMVA |
title | Fast Inference for Machine Learning in ROOT/TMVA |
title_full | Fast Inference for Machine Learning in ROOT/TMVA |
title_fullStr | Fast Inference for Machine Learning in ROOT/TMVA |
title_full_unstemmed | Fast Inference for Machine Learning in ROOT/TMVA |
title_short | Fast Inference for Machine Learning in ROOT/TMVA |
title_sort | fast inference for machine learning in root/tmva |
topic | Computing and Computers |
url | https://dx.doi.org/10.1051/epjconf/202024506008 http://cds.cern.ch/record/2752851 |
work_keys_str_mv | AT albertssonkim fastinferenceformachinelearninginroottmva AT ansitong fastinferenceformachinelearninginroottmva AT monetalorenzo fastinferenceformachinelearninginroottmva AT wunschstefan fastinferenceformachinelearninginroottmva AT zampieriluca fastinferenceformachinelearninginroottmva |