{
  "id": "1402.2300",
  "version": "v1",
  "published": "2014-02-10T21:05:58.000Z",
  "updated": "2014-02-10T21:05:58.000Z",
  "title": "Feature and Variable Selection in Classification",
  "authors": [
    "Aaron Karper"
  ],
  "comment": "Part of master seminar in document analysis held by Marcus Eichenberger-Liwicki",
  "categories": [
    "cs.LG",
    "cs.AI",
    "stat.ML"
  ],
  "abstract": "The amount of information in the form of features and variables avail- able to machine learning algorithms is ever increasing. This can lead to classifiers that are prone to overfitting in high dimensions, high di- mensional models do not lend themselves to interpretable results, and the CPU and memory resources necessary to run on high-dimensional datasets severly limit the applications of the approaches. Variable and feature selection aim to remedy this by finding a subset of features that in some way captures the information provided best. In this paper we present the general methodology and highlight some specific approaches.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2014-02-10T21:05:58.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "variable selection",
      "classification",
      "feature selection aim",
      "high-dimensional datasets severly limit",
      "memory resources necessary"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2014arXiv1402.2300K"
    }
  }
}