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 1810.03548cs.LGstat.ML
收藏

元学习研究综述

Meta-Learning: A Survey

Eindhoven University of Technology(埃因霍温理工大学)

Joaquin Vanschoren

摘要:

元学习,或学习学习,是系统地观察不同的机器学习方法如何在广泛的学习任务上执行的科学,然后从这种经验或元数据中学习,以比其他方式更快地学习新任务。这不仅大大加快和改进了机器学习管道或神经架构的设计,还允许我们用以数据驱动方式学习的新方法取代手工设计的算法。在这一章中,我们提供了在这个迷人的和不断发展的领域的艺术状态的概述。

英文摘要:

Meta-learning, or learning to learn, is the science of systematically observing how different machine learning approaches perform on a wide range of learning tasks, and then learning from this experience, or meta-data, to learn new tasks much faster than otherwise possible. Not only does this dramatically speed up and improve the design of machine learning pipelines or neural architectures, it also allows us to replace hand-engineered algorithms with novel approaches learned in a data-driven way. In this chapter, we provide an overview of the state of the art in this fascinating and continuously evolving field.

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。

↑