{
  "id": 6991,
  "title": "Congratulations!",
  "url": "/competitions/dogs-vs-cats/discussion/6991",
  "author_name": "DaggerFS",
  "post_date": "2014-02-02T22:00:00.797000",
  "votes": 23,
  "comment_count": 0,
  "views": 3162,
  "content": "<p>I'd like to express my sincere congratulations to Pierre Sermanet, and everyone who did great on this challenge! And of course - kudos to deep convolutional networks!</p>\n<p>I haven't been following the thread too much after Jeff and I did our benchmark submission based on decaf. I am quite surprised but at the same time honored that people have used decaf to achieve nice results, and I am much grateful on that!</p>\n<p>Hopefully I can provide some more pointers to recent CNN approaches that people will be interested in:</p>\n<p>(1) The winning algorithm, OverFeat, has been published here:</p>\n<p>http://arxiv.org/abs/1312.6229</p>\n<p>which details the overall architecture and training details. As far as I understand Pierre followed the same approach (according to his Google+ post):</p>\n<p>https://plus.google.com/+PierreSermanet/posts/GxZHEH9ynoj</p>\n<p>(2) After decaf we have released caffe, which is a C++/GPU implementation of both training and deploying CNNs. Hopefully some would be interested in using this beyond academia - it's BSD licensed!</p>\n<p>http://daggerfs.com/caffe/</p>\n<p>(3) Beyond dogs and cats, the winner of the ImageNet challenge this year, Matt Zeiler, also has an excellent paper on visualizing and understanding CNN models:</p>\n<p>http://arxiv.org/abs/1311.2901</p>\n<p>&nbsp;</p>\n<p>Hope you enjoyed and will continue to enjoy deep learning along the journey :)</p>",
  "messages": [
    {
      "id": 38284,
      "postDate": "2014-02-02T22:00:00.797Z",
      "content": "<p>I'd like to express my sincere congratulations to Pierre Sermanet, and everyone who did great on this challenge! And of course - kudos to deep convolutional networks!</p>\n<p>I haven't been following the thread too much after Jeff and I did our benchmark submission based on decaf. I am quite surprised but at the same time honored that people have used decaf to achieve nice results, and I am much grateful on that!</p>\n<p>Hopefully I can provide some more pointers to recent CNN approaches that people will be interested in:</p>\n<p>(1) The winning algorithm, OverFeat, has been published here:</p>\n<p>http://arxiv.org/abs/1312.6229</p>\n<p>which details the overall architecture and training details. As far as I understand Pierre followed the same approach (according to his Google+ post):</p>\n<p>https://plus.google.com/+PierreSermanet/posts/GxZHEH9ynoj</p>\n<p>(2) After decaf we have released caffe, which is a C++/GPU implementation of both training and deploying CNNs. Hopefully some would be interested in using this beyond academia - it's BSD licensed!</p>\n<p>http://daggerfs.com/caffe/</p>\n<p>(3) Beyond dogs and cats, the winner of the ImageNet challenge this year, Matt Zeiler, also has an excellent paper on visualizing and understanding CNN models:</p>\n<p>http://arxiv.org/abs/1311.2901</p>\n<p>&nbsp;</p>\n<p>Hope you enjoyed and will continue to enjoy deep learning along the journey :)</p>",
      "votes": 22
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "38284": ""
  }
}