TMVA Deep Learning Developments - 3D Convolutions


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 have expanded TMVA’s capabilities to include a deep learning library (DNN) supporting 2D convolutional layers with training on both CPU and GPUs. This summer we would like to expand the toolkit with 3D convolutional operators implemented, both for CPU and GPU. For the GPU case, the implementation will be based on the cuDNN library. 3D CNNs have very promising applications in particle physics, such as imaging calorimetry and particle tracking, allowing physicists to use new techniques to identify particles and search for new physics. In addition they can be used as Generative Adversarial Networks for fast imaging detector simulations.

Task ideas and expected results


Strong C++ skills, solid knowledge of deep learning, familiarity with GPUs


Please DO NOT contact mentors directly by email, and instead please send project inquiries to with Project Title in the subject and relevant mentors will get in touch with you.

Corresponding Project

Participating Organizations