{
  "id": 32065,
  "title": "PCA should be used?",
  "url": "/competitions/noaa-fisheries-steller-sea-lion-population-count/discussion/32065",
  "author_name": "",
  "post_date": "2017-04-25T14:46:46.773787800Z",
  "votes": null,
  "comment_count": 3,
  "views": 0,
  "content": "<p>I am new to Data Science. I am reading Principal Component Analysis. I understand it is used in Facial Recognition. So was just wondering if PCA should be applied to this problem? If not please explain why?</p>",
  "messages": [
    {
      "id": "177670",
      "postDate": "04/25/2017 14:46:46",
      "content": "<p>I am new to Data Science. I am reading Principal Component Analysis. I understand it is used in Facial Recognition. So was just wondering if PCA should be applied to this problem? If not please explain why?</p>",
      "rawMarkdown": "I am new to Data Science. I am reading Principal Component Analysis. I understand it is used in Facial Recognition. So was just wondering if PCA should be applied to this problem? If not please explain why?",
      "votes": null
    },
    {
      "id": "177992",
      "postDate": "04/26/2017 11:50:05",
      "content": "<p>In this competition, we don't have to focus on faces of sea lions.<br>\nSome techniques used in facial <em>detection</em> may help us rather than <em>recognition</em>. </p>",
      "rawMarkdown": "In this competition, we don't have to focus on faces of sea lions.<br>\nSome techniques used in facial *detection* may help us rather than *recognition*.",
      "votes": null
    },
    {
      "id": "177996",
      "postDate": "04/26/2017 12:05:50",
      "content": "<p>Thank you for your reply...I figured out that indeed this competition is focused on correctly counting sealions (male adult, female, etc) in the images provided in the dataset.\nPCA could still be used in it?  Could you or anyone else can answer that? Basically I am looking for practical use cases where PCA should be applied/used. Its for dimentionality / feature reduction when there are too many dimensions. Does this problem needs such transformations?</p>",
      "rawMarkdown": "Thank you for your reply...I figured out that indeed this competition is focused on correctly counting sealions (male adult, female, etc) in the images provided in the dataset.\nPCA could still be used in it?  Could you or anyone else can answer that? Basically I am looking for practical use cases where PCA should be applied/used. Its for dimentionality / feature reduction when there are too many dimensions. Does this problem needs such transformations?",
      "votes": null
    },
    {
      "id": "178037",
      "postDate": "04/26/2017 13:55:28",
      "content": "<p>I don't think there is a simple yes or no answer to your question. PCA could be one step in the pipeline, but it is also possible to solve this problem without PCA. </p>",
      "rawMarkdown": "I don't think there is a simple yes or no answer to your question. PCA could be one step in the pipeline, but it is also possible to solve this problem without PCA.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 177992,
      "author_name": "toshik",
      "author_url": "",
      "post_date": "04/26/2017 11:50:05",
      "content": "<p>In this competition, we don't have to focus on faces of sea lions.<br>\nSome techniques used in facial <em>detection</em> may help us rather than <em>recognition</em>. </p>",
      "votes": null,
      "replies": [
        {
          "id": 177996,
          "author_name": "abverma",
          "author_url": "",
          "post_date": "04/26/2017 12:05:50",
          "content": "<p>Thank you for your reply...I figured out that indeed this competition is focused on correctly counting sealions (male adult, female, etc) in the images provided in the dataset.\nPCA could still be used in it?  Could you or anyone else can answer that? Basically I am looking for practical use cases where PCA should be applied/used. Its for dimentionality / feature reduction when there are too many dimensions. Does this problem needs such transformations?</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 178037,
          "author_name": "andraszsom",
          "author_url": "",
          "post_date": "04/26/2017 13:55:28",
          "content": "<p>I don't think there is a simple yes or no answer to your question. PCA could be one step in the pipeline, but it is also possible to solve this problem without PCA. </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "177670": "I am new to Data Science. I am reading Principal Component Analysis. I understand it is used in Facial Recognition. So was just wondering if PCA should be applied to this problem? If not please explain why?",
    "177992": "In this competition, we don't have to focus on faces of sea lions.<br>\nSome techniques used in facial *detection* may help us rather than *recognition*.",
    "177996": "Thank you for your reply...I figured out that indeed this competition is focused on correctly counting sealions (male adult, female, etc) in the images provided in the dataset.\nPCA could still be used in it?  Could you or anyone else can answer that? Basically I am looking for practical use cases where PCA should be applied/used. Its for dimentionality / feature reduction when there are too many dimensions. Does this problem needs such transformations?",
    "178037": "I don't think there is a simple yes or no answer to your question. PCA could be one step in the pipeline, but it is also possible to solve this problem without PCA."
  },
  "source": "meta"
}