{
  "id": "2102.12985",
  "version": "v1",
  "published": "2021-02-22T04:34:29.000Z",
  "updated": "2021-02-22T04:34:29.000Z",
  "title": "A Novel Framework for Neural Architecture Search in the Hill Climbing Domain",
  "authors": [
    "Mudit Verma",
    "Pradyumna Sinha",
    "Karan Goyal",
    "Apoorva Verma",
    "Seba Susan"
  ],
  "comment": "8 pages, 6 figures",
  "doi": "10.1109/AIKE.2019.00009",
  "categories": [
    "cs.LG"
  ],
  "abstract": "Neural networks have now long been used for solving complex problems of image domain, yet designing the same needs manual expertise. Furthermore, techniques for automatically generating a suitable deep learning architecture for a given dataset have frequently made use of reinforcement learning and evolutionary methods which take extensive computational resources and time. We propose a new framework for neural architecture search based on a hill-climbing procedure using morphism operators that makes use of a novel gradient update scheme. The update is based on the aging of neural network layers and results in the reduction in the overall training time. This technique can search in a broader search space which subsequently yields competitive results. We achieve a 4.96% error rate on the CIFAR-10 dataset in 19.4 hours of a single GPU training.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-02-22T04:34:29.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "neural architecture search",
      "hill climbing domain",
      "novel framework",
      "novel gradient update scheme",
      "broader search space"
    ],
    "tags": [
      "journal article"
    ],
    "publication": {
      "publisher": "IEEE"
    },
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}