Machine learning for surface prediction in ACTS
This work addresses navigation challenges in particle physics track reconstruction, but appears incremental as it focuses on comparing existing methods without introducing new paradigms.
The paper tackles the problem of machine-learning-assisted navigation for track reconstruction in detectors by investigating different neural network training approaches for surface prediction within the ACTS tracking toolkit, but does not report specific results or numbers.
We present an ongoing R&D activity for machine-learning-assisted navigation through detectors to be used for track reconstruction. We investigate different approaches of training neural networks for surface prediction and compare their results. This work is carried out in the context of the ACTS tracking toolkit.