Deep Learning 4: Error Analysis

threshold:

https://stackoverflow.com/questions/46224752/what-is-a-threshold-in-a-precision-recall-curve

In general, an instance would be classified as A, if P(A) > 0.5 (your threshold value).

For this value, you get your Recall-Precision pair based on the True Positives, True Negatives, False Positives and False Negatives.

dev example

clean up incorrect data

Deep Learning is Robust to Massive Label Noise: https://arxiv.org/abs/1705.10694

deep neural networks are capable of generalizing from training data for which true labels are massively

outnumbered by incorrect labels.

dev set error