Event Classification with Multi-step Machine Learning
| Autor: | K. Terashi, Tomoe Kishimoto, Junichi Tanaka, Yuya Kaneta, Yutaro Iiyama, Taichi Itoh, Ryu Sawada, Masahiko Saito, Yoshiaki Umeda |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Event (computing) Computer science business.industry Physics QC1-999 Inference Value (computer science) Machine learning computer.software_genre Machine Learning (cs.LG) Task (computing) Hyperparameter optimization Path (graph theory) Differentiable function Artificial intelligence business computer Selection (genetic algorithm) |
| Zdroj: | EPJ Web of Conferences, Vol 251, p 03036 (2021) |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|