scale standard deviations to 1

Fragment of a discussion from Talk:Firestarter/Version History
← Thread:Talk:Firestarter/Version History/scale standard deviations to 1/reply (2)

Jump to navigation Jump to search

Well, that's the easiest way I can think of... And it really surprised me that the standard deviation is almost the same for most bots. If so, then I think normalising standard deviation may not be that useful — since we already tune weights very hard. But for neural networks, I think this is invaluable, since we don't tune weights manually, and that would affect the learning speed a lot.

You do not have permission to edit this page, for the following reasons:

The action you have requested is limited to users in the group: Users.
You must confirm your email address before editing pages. Please set and validate your email address through your user preferences.

You can view and copy the source of this page.

I never thought about normalizing standard deviation for neural networks, because they should adjust themselves to the attributes anyways. But yeah, the learning speed is probably affected by it, I should consider that for further NN experiments :D

Return to Thread:Talk:Firestarter/Version History/scale standard deviations to 1/reply (3).

Retrieved from "http://robowiki.net/wiki/Thread:Talk:Firestarter/Version_History/scale_standard_deviations_to_1/reply_(2)#scale_standard_deviations_to_1_6064"