Event Classification with Multi-step Machine Learning

¹ International Center for Elementary Particle Physics, The University of Tokyo, 7-3-1 Hongo, Bunkyo, Tokyo, Japan
² BrainPad Inc., 3-2-10 Shirokanedai, Minato, Tokyo, Japan
³ Institute for AI and Beyond, The University of Tokyo, 7-3-1 Hongo, Bunkyo, Tokyo, Japan

^* e-mail: saito@icepp.s.u-tokyo.ac.jp
^** e-mail: jtanaka@icepp.s.u-tokyo.ac.jp

Published online: 23 August 2021

Abstract

The usefulness and value of Multi-step Machine Learning (ML), where a task is organized into connected sub-tasks with known intermediate inference goals, as opposed to a single large model learned end-to-end without intermediate sub-tasks, is presented. Pre-optimized ML models are connected and better performance is obtained by re-optimizing the connected one. The selection of an ML model from several small ML model candidates for each sub-task has been performed by using the idea based on Neural Architecture Search (NAS). In this paper, Differentiable Architecture Search (DARTS) and Single Path One-Shot NAS (SPOS-NAS) are tested, where the construction of loss functions is improved to keep all ML models smoothly learning. Using DARTS and SPOS-NAS as an optimization and selection as well as the connections for multi-step machine learning systems, we find that (1) such a system can quickly and successfully select highly performant model combinations, and (2) the selected models are consistent with baseline algorithms, such as grid search, and their outputs are well controlled.