Викторина за активно учене

Отговорите и обясненията се появяват, докато отговаряте на теста.

1. Екипът разполага с голям набор от немаркирани данни, но има ограничено време на експертите. Какво моли активно обучение екипът да маркира следващо?
   • Every example in a fixed order
   • Only examples the model already predicts with high confidence
   • Examples selected as informative for the current model
   • Only examples generated synthetically by the model
2. В цикъла на активно обучение в ръководството какво представлява оракулът?
   • The human expert or other source that supplies requested labels
   • The unlabeled pool before any selection
   • The model’s probability score for a class
   • The evaluation metric computed after training
3. Два класификатора на продукти се разминават силно относно категория. Коя стратегия би приоритизирала този пример за маркиране?
   • Random data augmentation
   • Градиентно изрязване
   • Label smoothing
   • Query-by-committee
4. Класификаторът присвоява почти равни вероятности на два класа за немаркиран елемент. Защо несигурностното семплиране би го запитало?
   • Its label has already been confirmed
   • The small probability margin signals uncertainty about its label
   • It is guaranteed to be mislabeled
   • It has the highest possible confidence
5. Защо селекторът на партиди комбинира разнообразие с несигурност?
   • To avoid repeatedly selecting uncertain cases from only one narrow region
   • To eliminate all human annotation
   • To make the model linear
   • To guarantee every selected label is correct
6. A radiology team can afford only a small number of expert annotations. Which use best matches the guide?
   • Let the model diagnose without expert review
   • Label only scans already known to be easy
   • Prioritize ambiguous scans for radiologists to label, then assess the trained model
   • Claim that fewer labels always yield the same accuracy
7. What happens after the oracle labels a selected batch in the pool-based loop?
   • The model discards its labeled set and starts over
   • The new labels are added to training and selection repeats
   • The unlabeled pool becomes a test set automatically
   • Human review is permanently removed
8. Which statement best describes a successful active-learning result?
   • Every dataset always needs exactly half as many labels
   • The model chooses labels without any human involvement
   • Uncertainty sampling can never introduce bias
   • Comparable model performance may be reached with fewer paid annotations