{
  "id": "2210.13441",
  "version": "v1",
  "published": "2022-10-24T17:54:46.000Z",
  "updated": "2022-10-24T17:54:46.000Z",
  "title": "Bridging Machine Learning and Sciences: Opportunities and Challenges",
  "authors": [
    "Taoli Cheng"
  ],
  "comment": "8 pages, 3 figures",
  "categories": [
    "stat.ML",
    "cs.LG",
    "hep-ex",
    "hep-ph",
    "physics.data-an"
  ],
  "abstract": "The application of machine learning in sciences has seen exciting advances in recent years. As a widely-applicable technique, anomaly detection has been long studied in the machine learning community. Especially, deep neural nets-based out-of-distribution detection has made great progress for high-dimensional data. Recently, these techniques have been showing their potential in scientific disciplines. We take a critical look at their applicative prospects including data universality, experimental protocols, model robustness, etc. We discuss examples that display transferable practices and domain-specific challenges simultaneously, providing a starting point for establishing a novel interdisciplinary research paradigm in the near future.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-10-24T17:54:46.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "bridging machine learning",
      "challenges",
      "deep neural nets-based out-of-distribution detection",
      "opportunities",
      "novel interdisciplinary research paradigm"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}