Toolkit for Multivariate Analysis (TMVA) is a multi-purpose machine learning toolkit integrated into the ROOT scientific software framework, used in many particle physics data analysis and applications. We provide in TMVA the functionality for building deep neural networks including fully connected, convolutional and recurrent layers.
We have already a very efficient inference engine for decision tree based ML algorithms developed in TMVA. However, currently this engine only supports (xgBoost) model files. We would like to expand this support to existing TMVA XML formats and Scikit-learn pickles, as well as to support serialization of the model in ROOT format and conversion of other models into ROOT format.
Strong C++ skills, knowledge of decision tree based machine learning algorithms. Familiarity with GPUs is a huge plus.
Please DO NOT contact mentors directly by email, and instead please send project inquiries to MLSFT-GSOC@cern.ch with Project Title in the subject and relevant mentors will get in touch with you.