A tug-delay model's fold scores jump all over, while a second, too-simple model is equally weak on every fold. How should those evaluation patterns be read?
Select an answer to reveal the explanation.
Short Explanation
Jumping fold scores are high variance, the overfit risk. Equally weak folds are high bias, the underfit. Swap those labels and the trap snaps, and Rekognition does not read that pattern.
Full Explanation
High-variance evaluation behavior shows as fold scores that jump; that connects to overfitting. High bias shows as equally weak scores on every fold and connects to underfitting. Swapping those labels is the trap. Rekognition is not that reading.