http://robowiki.net/w/index.php?title=Thread:Talk:BeepBoop/Awesome_enty/reply_(21)&feed=atom&action=historyThread:Talk:BeepBoop/Awesome enty/reply (21) - Revision history2024-03-28T11:53:46ZRevision history for this page on the wikiMediaWiki 1.34.1http://robowiki.net/w/index.php?title=Thread:Talk:BeepBoop/Awesome_enty/reply_(21)&diff=56687&oldid=prevXor: Reply to Awesome enty2021-06-23T07:47:25Z<p>Reply to <a href="/wiki/Thread:Talk:BeepBoop/Awesome_enty/reply_(17)" title="Thread:Talk:BeepBoop/Awesome enty/reply (17)">Awesome enty</a></p>
<p><b>New page</b></p><div>One more detail, are you doing any encoding before inputting them into the NN part? I remembered [[Darkcanuck]] had some rather succesful attempt in NN (end-to-end), by binning features like the old VCS ways. <br />
<br />
And since most features are essentially tabular, apart from the NN approaches with explicit feature interaction, GBDT can work very well as some feature transformation & interaction tool. There are also approaches using GBDT to do clustering, by converting clustering into classifying “dense” & “sparse” of space.</div>Xor