Event Classification with Multi-step Machine Learning
Event Classification with Multi-step Machine Learning
复制标题
DOI：
10.1051/epjconf/202125103036
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
M. Saito;T. Kishimoto;Yuya Kaneta;Taichi Itoh;Yoshiaki Umeda;J. Tanaka;Y. Iiyama;R. Sawada
中科院分区：
文献类型：
--
作者：
M. Saito;T. Kishimoto;Yuya Kaneta;Taichi Itoh;Yoshiaki Umeda;J. Tanaka;Y. Iiyama;R. Sawada
多步机器学习（ML）的有用性和价值，其中一个任务被组织成连接的子任务与已知的中间推理目标，而不是一个单一的大型模型学习端到端没有中间子任务，提出。预优化的ML模型被连接，并且通过重新优化连接的ML模型获得更好的性能。通过使用基于神经架构搜索（NAS）的思想，从每个子任务的几个小ML模型候选中选择ML模型。本文测试了可区分架构搜索（DARTS）和单路径单次NAS（SPOS-NAS），其中改进了损失函数的构造，以保持所有ML模型顺利学习。使用DARTS和SPOS-NAS作为多步机器学习系统的优化和选择以及连接，我们发现（1）这样的系统可以快速成功地选择高性能的模型组合，（2）所选模型与基线算法（如网格搜索）一致，并且它们的输出得到了很好的控制。
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.