Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele
Konge ati ÌRÁNTÍ adanwo
Distinguish precision from recall, calculate positive-class metrics, examine threshold tradeoffs, and interpret relevance among top-ranked results.
Ibeere 1 ti 8
Ibeere wo ni o dahun ni pipe?
Awotẹlẹ gbogbo ibeere8 ibeere
Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.
- Ibeere wo ni o dahun ni pipe?
- Ninu gbogbo awọn idaniloju gidi, melo ni a mu?
- Ninu gbogbo awọn ohun kan ti a sọ asọtẹlẹ rere, melo ni o daadaa nitootọ?
- Bawo ni deede awoṣe lapapọ?
- Awọn odi otitọ melo ni a rii?
- Ìrántí ni a tún mọ̀ sí:
- Ni pato
- Yiye
- Itọkasi
- Ifamọ (oṣuwọn rere gidi)
- On a fixed evaluation set, lowering a positive-class decision threshold usually produces which tradeoff?
- Recall can increase while precision can fall
- Precision and recall must increase by equal amounts
- The model necessarily predicts fewer positives
- Neither metric can ever change
- Fun idanwo ayẹwo aisan nibiti sisọnu alaisan alaisan ti buru pupọ ju itaniji eke lọ, o yẹ ki o ṣe pataki:
- Ga konge
- Ìrántí kekere
- Ga iranti
- Oṣuwọn odi otitọ nikan
- Dimegilio F1 jẹ asọye bi:
- Iṣiro tumosi ti konge ati ÌRÁNTÍ
- Itumọ ti irẹpọ ti konge ati ÌRÁNTÍ
- Apao ti konge ati ÌRÁNTÍ
- Ọja ti deede ati ÌRÁNTÍ
- Why can precision and recall reveal a weakness hidden by high accuracy on a dataset dominated by negatives?
- They focus on positive predictions and actual positives instead of rewarding a large true-negative count
- They measure the true-negative rate directly
- They must both exceed accuracy
- They guarantee reliability regardless of sample size
- A classifier has 20 true positives, 5 false positives, and 10 false negatives. Which precision and recall values follow?
- Precision 2/3; recall 4/5
- Precision 20/35; recall 20/35
- Precision 1/4; recall 1/2
- Precision 4/5; recall 2/3
- Six of the top ten search results are relevant. What is precision@10 for that result list?
- 100%
- 40%
- 60%
- 6%