Hi, While "importing" the sse code to gnubg-nn I discovered an error in the sigmoid implementation. The calculation made by the see code did not match the one from the straight C code. (It was relatively easy for me to catch since sse can be toggled during run time in gnubg-nn)
Since this results in bad evaluations, I am surprised it has not been detected in gnubg. Has anyone did a real side-by-side comparison of gnubg with sse enabled and disabled? I would not like to make changes to gnubg, but encourage the people responsible for the sse code to have a look at gnubg-nn and see if they agree. -Joseph
_______________________________________________ Bug-gnubg mailing list [email protected] https://lists.gnu.org/mailman/listinfo/bug-gnubg
