[3N4-GS-10] AI application: model

[3N4-GS-10-01] Study of a learning method of multi-step deep learning model in particle physics experiment

〇Masahiko Saito^1,3, Masahiro Morinaga^1,3, Sanmay Ganguly^1,3, Tomoe Kishimoto^2,1,3, Junichi Tanaka^1,3 (1. International Center for Elementary Particle Physics, The University of Tokyo, 2. High Energy Accelerator Research Organization, 3. Institute for AI and Beyond, The University of Tokyo)

Keywords:Deep learning, Multi-step model, Multi-task learning

In particle physics experiments, for the data processing, several steps are required from raw experimental data to statistical analysis. In recent years, deep learning has been used in each step, contributing to the improvement of data analysis. If each deep learning model can be connected at once, its simultaneous training is expected to improve the performance of the last step, that is, results of the statistical analysis.
In this talk, we will discuss how to connect models and learn them simultaneously. We will show that (1) propagating the loss function for each step through an MLP mitigates degradation of the last step's performance, and (2) deep learning models having multiple loss functions can be effectively trained by applying techniques of multi-task learning.