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 2004.05439cs.LGstat.ML
收藏

神经网络中的元学习研究综述

Meta-Learning in Neural Networks: A Survey

Samsung AI Centre, Cambridge(三星人工智能中心剑桥);University of Edinburgh(爱丁堡大学)

Timothy Hospedales, Antreas Antoniou, Paul Micaelli, Amos Storkey

摘要:

近年来,人们对元学习(learning-to-learn)的兴趣急剧上升。与使用固定学习算法从头开始解决任务的传统人工智能方法相反,元学习旨在改进学习算法本身,给出多个学习片段的经验。这种范式为解决深度学习的许多传统挑战提供了机会,包括数据和计算瓶颈以及泛化。本调查描述了当代元学习的前景。我们首先讨论了元学习的定义,并将其与相关领域(如迁移学习和超参数优化)进行了定位。然后,我们提出了一个新的分类法,提供了一个更全面的细分空间的元学习方法今天。我们调查了元学习的应用前景和成功,如少样本学习和强化学习。最后,我们讨论了突出的挑战和有前途的未来研究领域。

英文摘要:

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where tasks are solved from scratch using a fixed learning algorithm, meta-learning aims to improve the learning algorithm itself, given the experience of multiple learning episodes. This paradigm provides an opportunity to tackle many conventional challenges of deep learning, including data and computation bottlenecks, as well as generalization. This survey describes the contemporary meta-learning landscape. We first discuss definitions of meta-learning and position it with respect to related fields, such as transfer learning and hyperparameter optimization. We then propose a new taxonomy that provides a more comprehensive breakdown of the space of meta-learning methods today. We survey promising applications and successes of meta-learning such as few-shot learning and reinforcement learning. Finally, we discuss outstanding challenges and promising areas for future research.

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。

↑