{
  "id": 163667,
  "title": "Just a thought on competition",
  "url": "/competitions/siim-isic-melanoma-classification/discussion/163667",
  "author_name": "",
  "post_date": "2020-07-03T02:10:13.085666700Z",
  "votes": 3,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Sometimes I feel like all the teams participating are neurons trying aggressively to converge and to find the lowest error on the problem. \"Prize money\" is something that decides how many layers are added to solve the problem. So it really depends how much the competition host can \"afford\" (Just like we think of trade off while using gpu vs cost). Eventually we as one \"network\" figure out the best way.  </p>",
  "messages": [
    {
      "id": "913126",
      "postDate": "07/03/2020 02:10:13",
      "content": "<p>Sometimes I feel like all the teams participating are neurons trying aggressively to converge and to find the lowest error on the problem. \"Prize money\" is something that decides how many layers are added to solve the problem. So it really depends how much the competition host can \"afford\" (Just like we think of trade off while using gpu vs cost). Eventually we as one \"network\" figure out the best way.  </p>",
      "rawMarkdown": "Sometimes I feel like all the teams participating are neurons trying aggressively to converge and to find the lowest error on the problem. \"Prize money\" is something that decides how many layers are added to solve the problem. So it really depends how much the competition host can \"afford\" (Just like we think of trade off while using gpu vs cost). Eventually we as one \"network\" figure out the best way.",
      "votes": null
    },
    {
      "id": "913196",
      "postDate": "07/03/2020 03:54:58",
      "content": "<p>Very interesting perspective <a href=\"/adityapatil673\">@adityapatil673</a> :) , and maybe the final LB could be thought of as final back-propagation? </p>",
      "rawMarkdown": "Very interesting perspective @adityapatil673 :) , and maybe the final LB could be thought of as final back-propagation?",
      "votes": null
    },
    {
      "id": "913861",
      "postDate": "07/03/2020 13:35:40",
      "content": "<p>Thanks man !</p>",
      "rawMarkdown": "Thanks man !",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 913196,
      "author_name": "binaicrai",
      "author_url": "",
      "post_date": "07/03/2020 03:54:58",
      "content": "<p>Very interesting perspective <a href=\"/adityapatil673\">@adityapatil673</a> :) , and maybe the final LB could be thought of as final back-propagation? </p>",
      "votes": null,
      "replies": [
        {
          "id": 913861,
          "author_name": "adityapatil673",
          "author_url": "",
          "post_date": "07/03/2020 13:35:40",
          "content": "<p>Thanks man !</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "913126": "Sometimes I feel like all the teams participating are neurons trying aggressively to converge and to find the lowest error on the problem. \"Prize money\" is something that decides how many layers are added to solve the problem. So it really depends how much the competition host can \"afford\" (Just like we think of trade off while using gpu vs cost). Eventually we as one \"network\" figure out the best way.",
    "913196": "Very interesting perspective @adityapatil673 :) , and maybe the final LB could be thought of as final back-propagation?",
    "913861": "Thanks man !"
  },
  "source": "meta"
}