{
  "id": 9871,
  "title": "Signal Processing",
  "url": "/competitions/decoding-the-human-brain/discussion/9871",
  "author_name": "",
  "post_date": "2014-07-28T04:17:43.323Z",
  "votes": null,
  "comment_count": 1,
  "views": 1113,
  "content": "<p>I found that I was able to get slightly better scores on Triskelion's python script and Vowpal Wabbit by simply running a Fourier transform on the data.&nbsp; I am under the impression that Fourier transform shouldn't change the performance of features with a linear classifier.&nbsp; Does anybody know if this is true? And if so, does anyone have a guess why I would have noticed a difference (perhaps to do with rounding of very small decimals)?</p>",
  "messages": [
    {
      "id": "51242",
      "postDate": "07/28/2014 04:17:43",
      "content": "<p>I found that I was able to get slightly better scores on Triskelion's python script and Vowpal Wabbit by simply running a Fourier transform on the data.&nbsp; I am under the impression that Fourier transform shouldn't change the performance of features with a linear classifier.&nbsp; Does anybody know if this is true? And if so, does anyone have a guess why I would have noticed a difference (perhaps to do with rounding of very small decimals)?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "51247",
      "postDate": "07/28/2014 04:58:36",
      "content": "<p>If you took the magnitude, then it might make sense. &nbsp;It's likely that phase information is basically just noise. &nbsp;FT + magnitude deletes the phase information.</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 51247,
      "author_name": "phillipadkins",
      "author_url": "",
      "post_date": "07/28/2014 04:58:36",
      "content": "<p>If you took the magnitude, then it might make sense. &nbsp;It's likely that phase information is basically just noise. &nbsp;FT + magnitude deletes the phase information.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "51242": "",
    "51247": ""
  },
  "source": "meta"
}