Image Classification

Five questions. Choose one answer for each, then submit to see your score and explanations.

The practice target is 80%. You can retry as often as you like, and every lesson stays accessible.

You can practice as a guest. Sign in before starting an attempt to save your scores.

1. Which explanation matches start with a feature-based baseline?A. Nearest-neighbor classification predicts from labeled examples close under a chosen representation and distance.B. Probabilistic models estimate scores under assumptions; margin methods seek separating boundaries.C. Confident errors deserve review of labels, shortcuts, calibration, and unusual conditions.D. A feature-based baseline measures interpretable color, texture, or shape summaries before classification.

2. Which explanation matches nearest-neighbor classification of images?A. A feature-based baseline measures interpretable color, texture, or shape summaries before classification.B. Probabilistic models estimate scores under assumptions; margin methods seek separating boundaries.C. Nearest-neighbor classification predicts from labeled examples close under a chosen representation and distance.D. Confident errors deserve review of labels, shortcuts, calibration, and unusual conditions.

3. Which explanation matches probabilistic and margin-based alternatives?A. A feature-based baseline measures interpretable color, texture, or shape summaries before classification.B. Probabilistic models estimate scores under assumptions; margin methods seek separating boundaries.C. Nearest-neighbor classification predicts from labeled examples close under a chosen representation and distance.D. Confident errors deserve review of labels, shortcuts, calibration, and unusual conditions.

4. For nearest-neighbor classification of images, which result or action fits this practical case: A bent parking sign resembles several stored intact signs.A. Compare one candidate to its closest damaged and intact training signs.B. Fit the baseline only on training images and compare it on held-out parking signs.C. Compare a calibrated probability estimate with a margin score before choosing a review threshold.D. Inspect the image, the training neighborhood, and lighting before adding more data.

5. For inspect confident classification mistakes, which result or action fits this practical case: A classifier confidently calls a bent sign undamaged.A. Fit the baseline only on training images and compare it on held-out parking signs.B. Compare one candidate to its closest damaged and intact training signs.C. Compare a calibrated probability estimate with a margin score before choosing a review threshold.D. Inspect the image, the training neighborhood, and lighting before adding more data.

Review this module from its first lesson →

Image Classification

Your result