Konstantin Shmelkov

Results 12 comments of Konstantin Shmelkov

It makes much more sense now, thank you. However, I don't see how it is specific to CTC cost. If it is related only to softmax/cross-entropy, it must be a...

Well, I have done some experiments on my tasks. I agree that `pseudo_cost` behaves somewhat more stable, but I couldn't find a pattern (i.e. the effect is inconsistent). For my...