{
  "id": "2101.05795",
  "version": "v1",
  "published": "2021-01-14T18:57:29.000Z",
  "updated": "2021-01-14T18:57:29.000Z",
  "title": "A Metaheuristic-Driven Approach to Fine-Tune Deep Boltzmann Machines",
  "authors": [
    "Leandro Aparecido Passos",
    "João Paulo Papa"
  ],
  "comment": "30 pages, 7 figures",
  "journal": "Applied Soft Computing 97 (2020): 105717",
  "doi": "10.1016/j.asoc.2019.105717",
  "categories": [
    "cs.LG"
  ],
  "abstract": "Deep learning techniques, such as Deep Boltzmann Machines (DBMs), have received considerable attention over the past years due to the outstanding results concerning a variable range of domains. One of the main shortcomings of these techniques involves the choice of their hyperparameters, since they have a significant impact on the final results. This work addresses the issue of fine-tuning hyperparameters of Deep Boltzmann Machines using metaheuristic optimization techniques with different backgrounds, such as swarm intelligence, memory- and evolutionary-based approaches. Experiments conducted in three public datasets for binary image reconstruction showed that metaheuristic techniques can obtain reasonable results.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-01-14T18:57:29.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "fine-tune deep boltzmann machines",
      "metaheuristic-driven approach",
      "metaheuristic optimization techniques",
      "binary image reconstruction",
      "deep learning techniques"
    ],
    "tags": [
      "journal article"
    ],
    "publication": {
      "publisher": "Elsevier"
    },
    "note": {
      "typesetting": "TeX",
      "pages": 30,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}