{
  "id": "2004.08083",
  "version": "v1",
  "published": "2020-04-17T07:05:03.000Z",
  "updated": "2020-04-17T07:05:03.000Z",
  "title": "Meta-Meta-Classification for One-Shot Learning",
  "authors": [
    "Arkabandhu Chowdhury",
    "Dipak Chaudhari",
    "Swarat Chaudhuri",
    "Chris Jermaine"
  ],
  "comment": "8 pages without references, 2 figures",
  "categories": [
    "cs.LG",
    "cs.CV",
    "stat.ML"
  ],
  "abstract": "We present a new approach, called meta-meta-classification, to learning in small-data settings. In this approach, one uses a large set of learning problems to design an ensemble of learners, where each learner has high bias and low variance and is skilled at solving a specific type of learning problem. The meta-meta classifier learns how to examine a given learning problem and combine the various learners to solve the problem. The meta-meta-learning approach is especially suited to solving few-shot learning tasks, as it is easier to learn to classify a new learning problem with little data than it is to apply a learning algorithm to a small data set. We evaluate the approach on a one-shot, one-class-versus-all classification task and show that it is able to outperform traditional meta-learning as well as ensembling approaches.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-04-17T07:05:03.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "learning problem",
      "one-shot learning",
      "meta-meta-classification",
      "one-class-versus-all classification task",
      "small data set"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}