arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.01184cs.LGcs.SYeess.SY
收藏

为系统设计和运行经验测量传输距离

Empirically Measuring Transfer Distance for System Design and Operation

University of Virginia(弗吉尼亚大学)

Tyler Cody, Stephen Adams, Peter A. Beling

摘要:

经典的机器学习方法对非平稳性敏感。迁移学习可以通过将知识从一个系统共享到另一个系统来解决非平稳性问题,然而,在机器自动化和国防等领域,数据从根本上是有限的。因此,迁移学习算法几乎没有(如果有的话)可供学习的示例。在这里,我们建议,这些约束的算法学习可以解决系统工程。我们正式定义一般的传输距离,并证明其使用经验量化模型的可转移性。我们考虑在机器重建程序的设计中使用转移距离,以允许可转移的预测模型。我们还考虑了在计算机视觉中使用转移距离来预测操作性能。从业者可以使用所提出的方法来设计和操作系统,考虑组件学习系统所面临的学习理论的挑战。

英文摘要:

Classical machine learning approaches are sensitive to non-stationarity. Transfer learning can address non-stationarity by sharing knowledge from one system to another, however, in areas like machine prognostics and defense, data is fundamentally limited. Therefore, transfer learning algorithms have little, if any, examples from which to learn. Herein, we suggest that these constraints on algorithmic learning can be addressed by systems engineering. We formally define transfer distance in general terms and demonstrate its use in empirically quantifying the transferability of models. We consider the use of transfer distance in the design of machine rebuild procedures to allow for transferable prognostic models. We also consider the use of transfer distance in predicting operational performance in computer vision. Practitioners can use the presented methodology to design and operate systems with consideration for the learning theoretic challenges faced by component learning systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑