{
  "id": "2004.11149",
  "version": "v1",
  "published": "2020-04-17T03:11:08.000Z",
  "updated": "2020-04-17T03:11:08.000Z",
  "title": "A Comprehensive Overview and Survey of Recent Advances in Meta-Learning",
  "authors": [
    "Huimin Peng"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "This article reviews meta-learning which seeks rapid and accurate model adaptation to unseen tasks with applications in image classification, natural language processing and robotics. Unlike deep learning, meta-learning uses few-shot datasets and concerns further improving model generalization to obtain higher prediction accuracy. We summarize meta-learning models in three categories: black-box adaptation, similarity based method and meta-learner procedure. Recent applications concentrate upon combination of meta-learning with Bayesian deep learning and reinforcement learning to provide feasible integrated problem solutions. We present performance comparison of recent meta-learning methods and discuss future research direction.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-04-17T03:11:08.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "meta-learning",
      "comprehensive overview",
      "accurate model adaptation",
      "higher prediction accuracy",
      "improving model generalization"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}