Difference between revisions of "Thread:Talk:BeepBoop/Awesome enty/reply (14)"

From Robowiki
Jump to navigation Jump to search
(Reply to Awesome enty)
 
(No difference)

Latest revision as of 15:06, 21 June 2021

It's possible that the KNN already takes that into account sufficiently. Maybe if you bump the cluster size up a lot, and change the kernel width for cluster weighting, it might force this part of the learning into the NN instead?