top | item 28753943 (no title) hchasestevens | 4 years ago Surely they must have already established a loss function in order to train the network in the first place? discuss order hn newest whimsicalism|4 years ago Sometimes the metric you use for the loss function is not the best metric for eval. Think BLEU for translation, for instance (not that BLEU is particularly great).
whimsicalism|4 years ago Sometimes the metric you use for the loss function is not the best metric for eval. Think BLEU for translation, for instance (not that BLEU is particularly great).
whimsicalism|4 years ago