![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F113660%2F7bb59980b9838b377d70e1851b9c6419%2FSelection_220.png?generation=1594226060511949&alt=media\")
ALASKA-3 can be a two-player game challenge .... It would be pretty fun to see kagglers against kagglers
\n\n
ALASKA-3 can be a two-player game challenge .... It would be pretty fun to see kagglers against kagglers
\n\n
It would also be nice if the same person won both tracks using a GAN.
", "rawMarkdown": "It would also be nice if the same person won both tracks using a GAN.", "votes": null }, { "id": "921903", "postDate": "07/09/2020 16:33:35", "content": "That would be VERY funny, yet quite difficult to organize ... how would you rate steganalysis when steganography is always changing ... \nBut why not organizing a challenge for DeepLearning of cost function for most efficient embedding ... given that the detector is fixed it seems a terrific idea ... if kaggle allows to do so, why not !
", "rawMarkdown": "That would be VERY funny, yet quite difficult to organize ... how would you rate steganalysis when steganography is always changing ... \nBut why not organizing a challenge for DeepLearning of cost function for most efficient embedding ... given that the detector is fixed it seems a terrific idea ... if kaggle allows to do so, why not !", "votes": null }, { "id": "921908", "postDate": "07/09/2020 16:40:14", "content": "there is a two player game challenge in kaggle : https://www.kaggle.com/c/connectx
\n\n\"You’ll also notice that the leaderboard is not based on how accurate your model is but rather how well you’ve performed against other users\". maybe it could be something like this:\nhttps://www.kaggle.com/c/connectx/overview/evaluation
", "rawMarkdown": "there is a two player game challenge in kaggle : https://www.kaggle.com/c/connectx\n\n\"You’ll also notice that the leaderboard is not based on how accurate your model is but rather how well you’ve performed against other users\". maybe it could be something like this:\nhttps://www.kaggle.com/c/connectx/overview/evaluation", "votes": null }, { "id": "921946", "postDate": "07/09/2020 17:13:55", "content": "Actually, this type of competitions have been organized before on Kaggle.
\n\nhttps://www.kaggle.com/c/nips-2017-defense-against-adversarial-attack/overview\nhttps://www.kaggle.com/c/nips-2017-targeted-adversarial-attack/overview\nhttps://www.kaggle.com/c/nips-2017-non-targeted-adversarial-attack/overview
", "rawMarkdown": "Actually, this type of competitions have been organized before on Kaggle.\n\nhttps://www.kaggle.com/c/nips-2017-defense-against-adversarial-attack/overview\nhttps://www.kaggle.com/c/nips-2017-targeted-adversarial-attack/overview\nhttps://www.kaggle.com/c/nips-2017-non-targeted-adversarial-attack/overview", "votes": null } ], "comments": [ { "id": 920863, "author_name": "felipekitamura", "author_url": "", "post_date": "07/08/2020 21:20:00", "content": "It would also be nice if the same person won both tracks using a GAN.
", "votes": null, "replies": [] }, { "id": 921903, "author_name": "remicogranne", "author_url": "", "post_date": "07/09/2020 16:33:35", "content": "That would be VERY funny, yet quite difficult to organize ... how would you rate steganalysis when steganography is always changing ... \nBut why not organizing a challenge for DeepLearning of cost function for most efficient embedding ... given that the detector is fixed it seems a terrific idea ... if kaggle allows to do so, why not !
", "votes": null, "replies": [ { "id": 921908, "author_name": "hengck23", "author_url": "", "post_date": "07/09/2020 16:40:14", "content": "there is a two player game challenge in kaggle : https://www.kaggle.com/c/connectx
\n\n\"You’ll also notice that the leaderboard is not based on how accurate your model is but rather how well you’ve performed against other users\". maybe it could be something like this:\nhttps://www.kaggle.com/c/connectx/overview/evaluation
", "votes": null, "replies": [] } ] }, { "id": 921946, "author_name": "wowfattie", "author_url": "", "post_date": "07/09/2020 17:13:55", "content": "Actually, this type of competitions have been organized before on Kaggle.
\n\nhttps://www.kaggle.com/c/nips-2017-defense-against-adversarial-attack/overview\nhttps://www.kaggle.com/c/nips-2017-targeted-adversarial-attack/overview\nhttps://www.kaggle.com/c/nips-2017-non-targeted-adversarial-attack/overview
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "920512": "ALASKA-3 can be a two-player game challenge .... It would be pretty fun to see kagglers against kagglers\n\n", "920863": "It would also be nice if the same person won both tracks using a GAN.", "921903": "That would be VERY funny, yet quite difficult to organize ... how would you rate steganalysis when steganography is always changing ... \nBut why not organizing a challenge for DeepLearning of cost function for most efficient embedding ... given that the detector is fixed it seems a terrific idea ... if kaggle allows to do so, why not !", "921908": "there is a two player game challenge in kaggle : https://www.kaggle.com/c/connectx\n\n\"You’ll also notice that the leaderboard is not based on how accurate your model is but rather how well you’ve performed against other users\". maybe it could be something like this:\nhttps://www.kaggle.com/c/connectx/overview/evaluation", "921946": "Actually, this type of competitions have been organized before on Kaggle.\n\nhttps://www.kaggle.com/c/nips-2017-defense-against-adversarial-attack/overview\nhttps://www.kaggle.com/c/nips-2017-targeted-adversarial-attack/overview\nhttps://www.kaggle.com/c/nips-2017-non-targeted-adversarial-attack/overview" }, "source": "meta" }