Paired Training Framework for Time-Constrained Learning
Paired Training Framework for Time-Constrained Learning
复制标题
DOI：
10.23919/date51398.2021.9473934
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
Jung-Eun Kim;Richard M. Bradford;Max Del Giudice;Zhong Shao
中科院分区：
文献类型：
--
作者：
Jung-Eun Kim;Richard M. Bradford;Max Del Giudice;Zhong Shao
本文提出了一个机器学习应用程序的设计框架，这些应用程序在时间是稀缺资源的网络物理系统等系统中运行。我们通过执行尽可能多的数据预处理来管理处理时间和解决方案质量之间的权衡。这种方法将我们引向一个设计框架，其中有两个独立的学习网络：一个用于预处理，一个用于核心应用程序功能。我们展示了这些网络如何一起训练，以及它们如何以随时随地的方式运行以优化性能。
This paper presents a design framework for machine learning applications that operate in systems such as cyber-physical systems where time is a scarce resource. We manage the tradeoff between processing time and solution quality by performing as much preprocessing of data as time will allow. This approach leads us to a design framework in which there are two separate learning networks: one for preprocessing and one for the core application functionality. We show how these networks can be trained together and how they can operate in an anytime fashion to optimize performance.