Ikibazo gihuza ibibazo · Hagati Urwego
Impuzandengo y'Ibisobanuro na PR-AUC Ikibazo
Witoze neza-kwibutsa ibicuruzwa biva mu mahanga, impuzandengo-yuzuye yo kubara n'ingaruka ziganje mugihe usuzumye icyitegererezo cyerekana ibyiza bidasanzwe.
Ikibazo 1 Bya 8
Ni igipimo ki precision ipima ku murongo w'isesengura watoranijwe?
Reba buri kibazo8 ibibazo
Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.
- Ni igipimo ki precision ipima ku murongo w'isesengura watoranijwe?
- The fraction of all positive cases that were selected
- The fraction of selected cases that are positive
- The fraction of all negative cases that were excluded
- The average score assigned to every unselected case
- Mu gutondeka hatarimo amanota angana, ibya mbere n'icya gatatu ni byo byiza gusa. Ni iyihe precision y'ubusanzwe ikurikira?
- 0.5
- 0.667
- 1.0
- About 0.833
- Kuki ubuso bwa trapezoidal PR-AUC bushobora gutandukana na precision y'ubusanzwe?
- They use different interpolation and summation rules
- Average precision averages precision equally across every threshold
- Trapezoidal PR-AUC weights only thresholds where a positive case enters
- Average precision always evaluates exactly one decision threshold
- Ni ibihe byinjiza bikomeza amakuru y'urutonde akeneye precision y'ubusanzwe?
- Only the final hard decisions and their total count
- Observed labels and one shared threshold, without per-case scores
- Observed labels and model prediction scores
- Only a confusion matrix at one threshold
- Dataseti ebyiri zifite ubwinshi butandukanye bw'ibintu byiza. Ni iki kigomba kujyana n'igereranya ry'amanota yabo ya precision-recall?
- Only overall accuracy on each dataset
- The positive fractions and evaluation sampling designs
- Only whether the two models use the same threshold
- Only whether the predicted scores occupy the same numeric range
- What happens to recall as a score threshold is lowered and more cases are included?
- It must strictly increase at every step
- It can decrease when a negative case is added
- It must become identical to precision
- It cannot decrease
- Why must tied prediction scores be handled carefully when calculating average precision?
- Equal-score cases cross a threshold together
- Changing the order of tied rows always leaves the no-ties rank shortcut unchanged
- A threshold can select tied positives before tied negatives
- Tied examples should each receive a different threshold based on their true labels
- A model has high average precision. Which deployment question still needs a separate check?
- Whether the model achieved a useful summary across thresholds
- Whether the reported summary used precision and recall
- Whether precision and workload are acceptable at the chosen operating threshold
- Whether recall increases were used as weights in the reported AP calculation