{
  "id": 4661,
  "title": "semi-supervised embedding",
  "url": "/competitions/challenges-in-representation-learning-the-black-box-learning-challenge/discussion/4661",
  "author_name": "",
  "post_date": "2013-05-23T05:25:53.597Z",
  "votes": null,
  "comment_count": 1,
  "views": 1428,
  "content": "<p>Is there any one who implemented weston's paper &quot;deep learning via semi-supervised embedding&quot; and submitted the results in this challenge?</p>\r\n<p>I would like to compare my method with the weston's method in this task.</p>\r\n<p>In pilot test on MNIST, the weston's results on the paper are better than my method without dropout.</p>\r\n<p></p>",
  "messages": [
    {
      "id": "24706",
      "postDate": "05/23/2013 05:25:53",
      "content": "<p>Is there any one who implemented weston's paper &quot;deep learning via semi-supervised embedding&quot; and submitted the results in this challenge?</p>\r\n<p>I would like to compare my method with the weston's method in this task.</p>\r\n<p>In pilot test on MNIST, the weston's results on the paper are better than my method without dropout.</p>\r\n<p></p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "24752",
      "postDate": "05/24/2013 05:00:35",
      "content": "<p>I don't think MNIST dataset is similar to the problem.</p>\r\n<p>In my case, same model in MNIST has a beautiful learning curve, but in this problem the curve is ugly no matter what learning rate I use.</p>\r\n<p></p>\r\n<p>[quote=sayit;24706]</p>\r\n<p>Is there any one who implemented weston's paper &quot;deep learning via semi-supervised embedding&quot; and submitted the results in this challenge?</p>\r\n<p>I would like to compare my method with the weston's method in this task.</p>\r\n<p>In pilot test on MNIST, the weston's results on the paper are better than my method without dropout.</p>\r\n<p></p>\r\n<p>[/quote]</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 24752,
      "author_name": "binghsu",
      "author_url": "",
      "post_date": "05/24/2013 05:00:35",
      "content": "<p>I don't think MNIST dataset is similar to the problem.</p>\r\n<p>In my case, same model in MNIST has a beautiful learning curve, but in this problem the curve is ugly no matter what learning rate I use.</p>\r\n<p></p>\r\n<p>[quote=sayit;24706]</p>\r\n<p>Is there any one who implemented weston's paper &quot;deep learning via semi-supervised embedding&quot; and submitted the results in this challenge?</p>\r\n<p>I would like to compare my method with the weston's method in this task.</p>\r\n<p>In pilot test on MNIST, the weston's results on the paper are better than my method without dropout.</p>\r\n<p></p>\r\n<p>[/quote]</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "24706": "",
    "24752": ""
  },
  "source": "meta"
}