JSAI2022

Presentation information

General Session

General Session » GS-10 AI application

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

Thu. Jun 16, 2022 3:30 PM - 5:10 PM Room N (Room 501)

座長:木佐森 慶一(NEC)[現地]

3:30 PM - 3:50 PM

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

〇Masahiko Saito1,3, Masahiro Morinaga1,3, Sanmay Ganguly1,3, Tomoe Kishimoto2,1,3, Junichi Tanaka1,3 (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.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password