Skip to content
ml-recall

#batches

1 question from Evaluation Metrics

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

hardAI-checkedEvaluation Metrics

A binary classifier is evaluated on an epoch of two batches. In batch 1 it predicts 4 positives, all correct (TP = 4, FP = 0). In batch 2 it predicts 6 positives, of which 2 are correct (TP = 2, FP = 4). The mean of the two per-batch precisions is , while the precision over the whole epoch is .

Fill in every blank (hints in the boxes). Enter moves to the next blank.