A survey of deep meta-learning

Author:

Huisman MikeORCID,van Rijn Jan N.ORCID,Plaat AskeORCID

Abstract

AbstractDeep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new concepts quickly is limited. Meta-learning is one approach to address this issue, by enabling the network to learn how to learn. The field of Deep Meta-Learning advances at great speed, but lacks a unified, in-depth overview of current techniques. With this work, we aim to bridge this gap. After providing the reader with a theoretical foundation, we investigate and summarize key methods, which are categorized into (i) metric-, (ii) model-, and (iii) optimization-based techniques. In addition, we identify the main open challenges, such as performance evaluations on heterogeneous benchmarks, and reduction of the computational costs of meta-learning.

Publisher

Springer Science and Business Media LLC

Subject

Artificial Intelligence,Linguistics and Language,Language and Linguistics

Reference94 articles.

1. Anderson T (2008) The theory and practice of online learning. AU Press, Athabasca University

2. Andrychowicz M, Denil M, Colmenarejo SG, Hoffman MW, Pfau D, Schaul T, Shillingford B, de Freitas N (2016) Learning to learn by gradient descent by gradient descent. In: Advances in neural information processing systems 29, Curran Associates Inc., NIPS’16, pp 3988–3996

3. Antoniou A, Edwards H, Storkey A (2019) How to train your MAML. In: International conference on learning representations, ICLR’19

4. Barrett DG, Hill F, Santoro A, Morcos AS, Lillicrap T (2018) Measuring abstract reasoning in neural networks. In: Proceedings of the 35th international conference on machine learning, JLMR.org, ICML’18, pp 4477–4486

5. Bengio S, Bengio Y, Cloutier J, Gecsei J (1997) On the optimization of a synaptic learning rule. In: Optimality in artificial and biological neural networks, Lawrance Erlbaum Associates, Inc

Cited by 218 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3