RNN-Time-series-Anomaly-Detection icon indicating copy to clipboard operation
RNN-Time-series-Anomaly-Detection copied to clipboard

Published 20 hours ago • verified publisher icon chickenbestlover

training loss function

Open jchenWill opened this issue 5 years ago • 1 comments

Hi Could you explain the three training loss you defined, free running, teacher forcing, and simplified professor force? or point out related papers? Thanks

jchenWill avatar May 29 '19 19:05 jchenWill

A useful blog post about 'free running' (using outputs as inputs) & 'teacher forcing' : post

Professor forcing paper: NIPS 2016

Simplified professor forcing is my idea which is a simplified version of professor forcing. While processor forcing requires a discriminator, simplified processor forcing does not require it.

chickenbestlover avatar Aug 21 '19 03:08 chickenbestlover