{
  "id": 135543,
  "title": "Slide Algorithm - might be a new era in deep learning",
  "url": "/competitions/deepfake-detection-challenge/discussion/135543",
  "author_name": "",
  "post_date": "2020-03-14T12:58:48.387228300Z",
  "votes": 4,
  "comment_count": 3,
  "views": 0,
  "content": "<p>Paper published on 01-03-2020\n<a href=\"https://arxiv.org/pdf/1903.03129.pdf\">https://arxiv.org/pdf/1903.03129.pdf</a></p>\n\n<p>Deep Learning Breakthrough Results In A 44-Core Intel Xeon Destroying NVIDIA Tesla V100 GPU\n<a href=\"https://wccftech.com/intel-ai-breakthrough-destroys-8-nvidia-v100-gpu/\">https://wccftech.com/intel-ai-breakthrough-destroys-8-nvidia-v100-gpu/</a></p>\n\n<p>SLIDE algorithm for training deep neural nets faster on CPUs than GPUs\n<a href=\"https://insidehpc.com/2020/03/slide-algorithm-for-training-deep-neural-nets-faster-on-cpus-than-gpus/\">https://insidehpc.com/2020/03/slide-algorithm-for-training-deep-neural-nets-faster-on-cpus-than-gpus/</a></p>",
  "messages": [
    {
      "id": "771647",
      "postDate": "03/14/2020 12:58:48",
      "content": "<p>Paper published on 01-03-2020\n<a href=\"https://arxiv.org/pdf/1903.03129.pdf\">https://arxiv.org/pdf/1903.03129.pdf</a></p>\n\n<p>Deep Learning Breakthrough Results In A 44-Core Intel Xeon Destroying NVIDIA Tesla V100 GPU\n<a href=\"https://wccftech.com/intel-ai-breakthrough-destroys-8-nvidia-v100-gpu/\">https://wccftech.com/intel-ai-breakthrough-destroys-8-nvidia-v100-gpu/</a></p>\n\n<p>SLIDE algorithm for training deep neural nets faster on CPUs than GPUs\n<a href=\"https://insidehpc.com/2020/03/slide-algorithm-for-training-deep-neural-nets-faster-on-cpus-than-gpus/\">https://insidehpc.com/2020/03/slide-algorithm-for-training-deep-neural-nets-faster-on-cpus-than-gpus/</a></p>",
      "rawMarkdown": "Paper published on 01-03-2020\nhttps://arxiv.org/pdf/1903.03129.pdf\n\nDeep Learning Breakthrough Results In A 44-Core Intel Xeon Destroying NVIDIA Tesla V100 GPU\nhttps://wccftech.com/intel-ai-breakthrough-destroys-8-nvidia-v100-gpu/\n\nSLIDE algorithm for training deep neural nets faster on CPUs than GPUs\nhttps://insidehpc.com/2020/03/slide-algorithm-for-training-deep-neural-nets-faster-on-cpus-than-gpus/",
      "votes": null
    },
    {
      "id": "771912",
      "postDate": "03/14/2020 19:36:41",
      "content": "<p>Don't sell your v100s just yet... </p>",
      "rawMarkdown": "Don't sell your v100s just yet...",
      "votes": null
    },
    {
      "id": "772003",
      "postDate": "03/14/2020 22:48:10",
      "content": "<p>Nice, now implement their same sparse algo directly in CUDA and get yet another boost...</p>",
      "rawMarkdown": "Nice, now implement their same sparse algo directly in CUDA and get yet another boost...",
      "votes": null
    },
    {
      "id": "772050",
      "postDate": "03/15/2020 00:42:21",
      "content": "<p>Unfortunately, CNN is not implemented in their github respiratory. Will definitely keep an eye on it!</p>",
      "rawMarkdown": "Unfortunately, CNN is not implemented in their github respiratory. Will definitely keep an eye on it!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 771912,
      "author_name": "moshel",
      "author_url": "",
      "post_date": "03/14/2020 19:36:41",
      "content": "<p>Don't sell your v100s just yet... </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 772003,
      "author_name": "hmendonca",
      "author_url": "",
      "post_date": "03/14/2020 22:48:10",
      "content": "<p>Nice, now implement their same sparse algo directly in CUDA and get yet another boost...</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 772050,
      "author_name": "unkownhihi",
      "author_url": "",
      "post_date": "03/15/2020 00:42:21",
      "content": "<p>Unfortunately, CNN is not implemented in their github respiratory. Will definitely keep an eye on it!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "771647": "Paper published on 01-03-2020\nhttps://arxiv.org/pdf/1903.03129.pdf\n\nDeep Learning Breakthrough Results In A 44-Core Intel Xeon Destroying NVIDIA Tesla V100 GPU\nhttps://wccftech.com/intel-ai-breakthrough-destroys-8-nvidia-v100-gpu/\n\nSLIDE algorithm for training deep neural nets faster on CPUs than GPUs\nhttps://insidehpc.com/2020/03/slide-algorithm-for-training-deep-neural-nets-faster-on-cpus-than-gpus/",
    "771912": "Don't sell your v100s just yet...",
    "772003": "Nice, now implement their same sparse algo directly in CUDA and get yet another boost...",
    "772050": "Unfortunately, CNN is not implemented in their github respiratory. Will definitely keep an eye on it!"
  },
  "source": "meta"
}