English

A Survey of Deep Meta-Learning

Machine Learning 2021-04-22 v2 Artificial Intelligence Machine Learning

Abstract

Deep 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.

Keywords

Cite

@article{arxiv.2010.03522,
  title  = {A Survey of Deep Meta-Learning},
  author = {Mike Huisman and Jan N. van Rijn and Aske Plaat},
  journal= {arXiv preprint arXiv:2010.03522},
  year   = {2021}
}

Comments

Published in the AI Review (AIRE) Journal (2021)

R2 v1 2026-06-23T19:08:22.899Z