Summada Kediska Fududeynta

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay calaamadaynta fududaynta isbeddelka ku saabsan yoolalka tababarka?
   • Waxay jilcisaa yoolalka hal-kulul si fasalka runta ahi uu ka hooseeyo 1.0 kuwa kalena waxyar bay ka sarreeyaan 0
   • Waxay meesha ka saartaa shaqada luminta
   • Waxay tirtirtaa fasallada khaldan
   • Waxay labanlaabtaa heerka waxbarashada
2. Qiimaha caadiga ah ee epsilon-ka fududaynta waa:
   • 0.9
   • 0.1
   • 5.0
   • 0.0
3. What is one intended effect of replacing hard one-hot targets with smoothed targets?
   • Force every class to have equal probability
   • Guarantee the largest possible logit for the true class
   • Avoid requiring the labeled class to receive a target probability of exactly one
   • Remove the need for labeled training data
4. Which landmark architectures are prominent examples of label-smoothing use?
   • AlexNet and LeNet only
   • ResNet-50 and VGG only
   • AlphaGo iyo AlphaZero
   • Inception-v3 iyo Transformer-ka
5. What can label smoothing do to calibration?
   • It can improve calibration in some settings, but the effect is task- and model-dependent
   • It guarantees perfect calibration for every classifier
   • It cannot affect predicted probabilities
   • It always makes confidence equal accuracy
6. Waa maxay dhinaca hoose ee la diiwaan galiyay ee summada fududaynta?
   • Had iyo jeer waxay yaraynaysaa saxnaanta
   • Waxay tirtiri kartaa isku ekaanshaha fasalka u dhexeeya, oo dhaawacaysa fogaynta aqoonta
   • Waxay u baahan tahay laba jeer xogta tababarka
   • Waxa kaliya oo ay ku shaqeysaa qoraalka
7. Why can label smoothing complicate knowledge distillation?
   • It converts every class label into an image
   • It forces the student to use a different tokenizer
   • It can remove information in logits about similarities among incorrect classes
   • It prevents the teacher from producing logits
8. What should a practitioner verify when comparing label-smoothing implementations?
   • Whether the model has a web browser
   • Whether training uses a validation filename
   • Whether logits are stored as text
   • Whether epsilon is distributed over all classes or only the non-target classes