ctak/include/weights.h, branch sixes An implementation of Tak and a computer opponent in C https://git.l-3.space/cgit/ctak/atom?h=sixes 2026-08-28T18:37:41Z Playing around with huge nn's, poorly trained. 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-03-28T03:59:33Z urn:sha1:35dc86f8476250f693aa419f404b2b4c8c381d92 Not great at shallow depths Rename ct_k -> ct, IANAL but ... 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-02-05T21:49:14Z urn:sha1:ce09b6d94ac3dbf426e959b14fd7731001a003d1 Added license information! 2026-08-28T18:37:41Z tslil clingman tslil@posteo.de 2021-01-29T02:30:30Z urn:sha1:a77062ce3dc9a99ad0662010cc7eeb00dd5036a6 Went back up to 1986 weights 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-16T19:08:46Z urn:sha1:50b9955b040005e489127a11cf9c1648438a6266 There was a bug in the minimax! 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-15T17:34:44Z urn:sha1:4ec810a2bb0ed393e59e0a03f8c98ec09805e989 Wider? 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-13T06:20:11Z urn:sha1:5159a45573f9b9c52814047816c418c2c450fde5 one output (of course), Pade approximant of logistic for activation 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-12T20:51:48Z urn:sha1:a96ec5a74093eb800d14e143b81302d3e0905b85 This finally works! 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-12T05:10:12Z urn:sha1:2fb71fcbc594c3a3f32ee0c95be2e4e9b9ae97df Close in principle, but there;s a bug in ct1997 &/ pptdb! 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-11T06:29:39Z urn:sha1:5d475f9dadcac74bde8262d600e68578e91323c9 This is the general idea, but i'm sure order is incorrect somewhere 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-11T02:40:38Z urn:sha1:b598a3ab9e682a826516b242a710b26e0c22389f