Accurate particle identification (PID) is one of the most important aspects of the LHCb experiment. Modern machine learning techniques such as neural networks (NNs) are efficiently applied to this problem and are integrated into the LHCb software. In this research, we discuss novel applications of neural network speed-up techniques to achieve faster PID in LHC upgrade conditions. We show that the best results are obtained using variational dropout sparsification, which provides a prediction (feedforward pass) speed increase of up to a factor of sixteen even when compared to a model with shallow networks.
Variational Dropout Sparsification for Particle Identification speed-up
Neural network speed-up techniques, particularly variational dropout sparsification, significantly enhance particle identification efficiency in LHC upgrade conditions.
- Year
- 2020
- Venue
- arXiv 2020
- Authors
- 3
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2001.07493ARXIV-DEFAULT
- TL;DR
- Semantic Scholar