{
  "id": 78112,
  "title": "Choosing validation set",
  "url": "/competitions/LANL-Earthquake-Prediction/discussion/78112",
  "author_name": "tnn",
  "post_date": "2019-01-19T21:59:45.819000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi,</p>\n\n<p>Can someone please elaborate on the type of validation data set used for this problem? We are using neural networks and finding that our models are overfitting the training data.</p>\n\n<p>Should we be choosing multiple validation datasets consisting of different types of acoustic fluctuations and time to failure values? Is using a k-fold cross-validation approach good for this problem?</p>\n\n<p>Thanks!</p>",
  "messages": [
    {
      "id": 458537,
      "postDate": "2019-01-19T21:59:45.820Z",
      "content": "<p>Hi,</p>\n\n<p>Can someone please elaborate on the type of validation data set used for this problem? We are using neural networks and finding that our models are overfitting the training data.</p>\n\n<p>Should we be choosing multiple validation datasets consisting of different types of acoustic fluctuations and time to failure values? Is using a k-fold cross-validation approach good for this problem?</p>\n\n<p>Thanks!</p>",
      "rawMarkdown": "Hi,\n\nCan someone please elaborate on the type of validation data set used for this problem? We are using neural networks and finding that our models are overfitting the training data.\n\nShould we be choosing multiple validation datasets consisting of different types of acoustic fluctuations and time to failure values? Is using a k-fold cross-validation approach good for this problem?\n\nThanks!"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "458537": "Hi,\n\nCan someone please elaborate on the type of validation data set used for this problem? We are using neural networks and finding that our models are overfitting the training data.\n\nShould we be choosing multiple validation datasets consisting of different types of acoustic fluctuations and time to failure values? Is using a k-fold cross-validation approach good for this problem?\n\nThanks!"
  }
}