CMS experiment currently uses machine learning algorithms at the Level-1 (hardware) trigger to estimate the momentum of traversing particles such as Muons. The first algorithm implemented in the trigger system was a discretized boosted decision tree. Currently, CMS is studying the use of deep learning algorithms at the trigger level that requires microsecond level latency and therefore requires highly optimized inference.
This project will focus on benchmarking, implementation and compression of deep learning algorithms for the trigger inference task. Currently implemented algorithms include boosted decision trees (BDTs), fully-connected deep neural networks (FCN) and convolutional neural networks (CNNs).
Python, C++, and some previous experience in Machine Learning.
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.