{
  "id": 250164,
  "title": "Deep Learning For Hidden Signals Papers and Video Presentation from NCSA",
  "url": "/competitions/g2net-gravitational-wave-detection/discussion/250164",
  "author_name": "",
  "post_date": "2021-07-01T11:14:16.956435900Z",
  "votes": 7,
  "comment_count": 3,
  "views": 0,
  "content": "<p>The presentation is titled: \"DEEP LEARNING FOR HIDDEN SIGNALS: REAL-TIME DETECTION AND PARAMETER ESTIMATION OF GRAVITATIONAL WAVES WITH CONVOLUTIONAL NEURAL NETWORKS\"</p>\n<p>It's by the GRAVITATIONAL ASTROPHYSICS RESEARCH AT National Center of Supercomputing Applications at the University of Illinois. </p>\n<p>Here is an excerpt: \"Current data analysis pipelines are limited by the extreme computational costs of template-based matched-filtering methods and thus are unable to scale to all types of sources.  We introduced Deep Filtering, a new method for end-to-end time-series signal processing which combines two deep convolutional neural networks to rapidly detect and estimate parameters of signals much weaker than the background noise.\"</p>\n<p><a href=\"https://gravity.ncsa.illinois.edu/research/deep-learning/real-time-detection-and-parameter-estimation/\" target=\"_blank\">And the best part is video presentations and two Publications</a>:  </p>\n<ol>\n<li><p>Deep neural networks to enable real-time multimessenger astronomy</p></li>\n<li><p>Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data</p></li>\n</ol>\n<p><a href=\"https://gravity.ncsa.illinois.edu/research/deep-learning/real-time-detection-and-parameter-estimation/\" target=\"_blank\">Enjoy it here</a>.</p>",
  "messages": [
    {
      "id": "1372023",
      "postDate": "07/01/2021 11:14:16",
      "content": "<p>The presentation is titled: \"DEEP LEARNING FOR HIDDEN SIGNALS: REAL-TIME DETECTION AND PARAMETER ESTIMATION OF GRAVITATIONAL WAVES WITH CONVOLUTIONAL NEURAL NETWORKS\"</p>\n<p>It's by the GRAVITATIONAL ASTROPHYSICS RESEARCH AT National Center of Supercomputing Applications at the University of Illinois. </p>\n<p>Here is an excerpt: \"Current data analysis pipelines are limited by the extreme computational costs of template-based matched-filtering methods and thus are unable to scale to all types of sources.  We introduced Deep Filtering, a new method for end-to-end time-series signal processing which combines two deep convolutional neural networks to rapidly detect and estimate parameters of signals much weaker than the background noise.\"</p>\n<p><a href=\"https://gravity.ncsa.illinois.edu/research/deep-learning/real-time-detection-and-parameter-estimation/\" target=\"_blank\">And the best part is video presentations and two Publications</a>:  </p>\n<ol>\n<li><p>Deep neural networks to enable real-time multimessenger astronomy</p></li>\n<li><p>Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data</p></li>\n</ol>\n<p><a href=\"https://gravity.ncsa.illinois.edu/research/deep-learning/real-time-detection-and-parameter-estimation/\" target=\"_blank\">Enjoy it here</a>.</p>",
      "rawMarkdown": "The presentation is titled: \"DEEP LEARNING FOR HIDDEN SIGNALS: REAL-TIME DETECTION AND PARAMETER ESTIMATION OF GRAVITATIONAL WAVES WITH CONVOLUTIONAL NEURAL NETWORKS\"\n\nIt's by the GRAVITATIONAL ASTROPHYSICS RESEARCH AT National Center of Supercomputing Applications at the University of Illinois. \n\nHere is an excerpt: \"Current data analysis pipelines are limited by the extreme computational costs of template-based matched-filtering methods and thus are unable to scale to all types of sources.  We introduced Deep Filtering, a new method for end-to-end time-series signal processing which combines two deep convolutional neural networks to rapidly detect and estimate parameters of signals much weaker than the background noise.\"\n\n[And the best part is video presentations and two Publications](https://gravity.ncsa.illinois.edu/research/deep-learning/real-time-detection-and-parameter-estimation/):  \n\n1. Deep neural networks to enable real-time multimessenger astronomy\n\n2. Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data\n\n[Enjoy it here](https://gravity.ncsa.illinois.edu/research/deep-learning/real-time-detection-and-parameter-estimation/).",
      "votes": null
    },
    {
      "id": "1373196",
      "postDate": "07/02/2021 09:47:32",
      "content": "<p>This is a great resource. Thanks <a href=\"https://www.kaggle.com/crained\" target=\"_blank\">@crained</a> </p>",
      "rawMarkdown": "This is a great resource. Thanks @crained",
      "votes": null
    },
    {
      "id": "1373283",
      "postDate": "07/02/2021 11:36:06",
      "content": "<p>No problem <a href=\"https://www.kaggle.com/paulrohan2020\" target=\"_blank\">@paulrohan2020</a> Hope it is helpful!</p>",
      "rawMarkdown": "No problem @paulrohan2020 Hope it is helpful!",
      "votes": null
    },
    {
      "id": "1561313",
      "postDate": "10/27/2021 13:14:11",
      "content": "<p>Hey,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "rawMarkdown": "Hey,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1373196,
      "author_name": "paulrohan2020",
      "author_url": "",
      "post_date": "07/02/2021 09:47:32",
      "content": "<p>This is a great resource. Thanks <a href=\"https://www.kaggle.com/crained\" target=\"_blank\">@crained</a> </p>",
      "votes": null,
      "replies": [
        {
          "id": 1373283,
          "author_name": "crained",
          "author_url": "",
          "post_date": "07/02/2021 11:36:06",
          "content": "<p>No problem <a href=\"https://www.kaggle.com/paulrohan2020\" target=\"_blank\">@paulrohan2020</a> Hope it is helpful!</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1561313,
      "author_name": "zerafachris",
      "author_url": "",
      "post_date": "10/27/2021 13:14:11",
      "content": "<p>Hey,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1372023": "The presentation is titled: \"DEEP LEARNING FOR HIDDEN SIGNALS: REAL-TIME DETECTION AND PARAMETER ESTIMATION OF GRAVITATIONAL WAVES WITH CONVOLUTIONAL NEURAL NETWORKS\"\n\nIt's by the GRAVITATIONAL ASTROPHYSICS RESEARCH AT National Center of Supercomputing Applications at the University of Illinois. \n\nHere is an excerpt: \"Current data analysis pipelines are limited by the extreme computational costs of template-based matched-filtering methods and thus are unable to scale to all types of sources.  We introduced Deep Filtering, a new method for end-to-end time-series signal processing which combines two deep convolutional neural networks to rapidly detect and estimate parameters of signals much weaker than the background noise.\"\n\n[And the best part is video presentations and two Publications](https://gravity.ncsa.illinois.edu/research/deep-learning/real-time-detection-and-parameter-estimation/):  \n\n1. Deep neural networks to enable real-time multimessenger astronomy\n\n2. Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data\n\n[Enjoy it here](https://gravity.ncsa.illinois.edu/research/deep-learning/real-time-detection-and-parameter-estimation/).",
    "1373196": "This is a great resource. Thanks @crained",
    "1373283": "No problem @paulrohan2020 Hope it is helpful!",
    "1561313": "Hey,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris"
  },
  "source": "meta"
}