{
  "id": "2010.03522",
  "version": "v1",
  "published": "2020-10-07T17:09:02.000Z",
  "updated": "2020-10-07T17:09:02.000Z",
  "title": "A Survey of Deep Meta-Learning",
  "authors": [
    "Mike Huisman",
    "Jan N. van Rijn",
    "Aske Plaat"
  ],
  "comment": "Extended version of book chapter in 'Metalearning: Applications to Automated Machine Learning and Data Mining' (2nd edition, forthcoming)",
  "categories": [
    "cs.LG",
    "cs.AI",
    "stat.ML"
  ],
  "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 quite limited. Meta-learning is one approach to address this issue, by enabling the network to learn how to learn. The exciting field of Deep Meta-Learning advances at great speed, but lacks a unified, insightful overview of current techniques. This work presents just that. 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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-10-07T17:09:02.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep meta-learning",
      "deep neural networks",
      "achieve great successes",
      "main open challenges",
      "large data sets"
    ],
    "tags": [
      "book chapter"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}