Property of gradient of cross-entropy loss with kernel density estimation
Fragment of a discussion from Talk:BeepBoop/Understanding BeepBoop
Jump to navigation
Jump to search
The thoughts on surfing & targeting is quite inspiring. And even if no data points are near within K size (hard case), that case is still valuable, since there may exist some data point just outside of the K size. And repeating the training process with new weight iteratively may eventually turn that case into an easy case ;) Are you doing something similar as well?
