A darkroom exposure advisor can memorize the training strips, miss the pattern on every strip, or land in between. What three outcomes should testers name, and when does the detection work sit?
Select an answer to reveal the explanation.
Short Explanation
A darkroom advisor can memorize the training strips (overfitting), miss the pattern on every strip (underfitting), or land in between (a right-fitting model). Detection belongs in training, evaluation, and tuning, not only after go-live, not only as a Chapter 3 split lecture, and not only as a closed-box adversarial pass.
Full Explanation
The three outcomes are overfitting, underfitting, and a right-fitting model, and over/underfit testing belongs in training, evaluation, and tuning. Operational drift only, a Chapter 3 split lecture, and adversarial volume-only miss that placement.