quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz buy nooy etiket

Dafay muur ay mébet yu nooy ak epsilon, effet etalonnage bu aju ci liggéey, kompromis distilaasioŋ, ak lu tax njariñ yi aju ci done yi ak mébet bi.

Yooni njiit yu jëm ciNooyal etiket
Laaj 1 de 8

Lan la etiketu nooy soppi ci wàllu tàggat yaram?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Lan la etiketu nooy soppi ci wàllu tàggat yaram?
    • Dafay yombal benn target bu tàng suko defee klaas dëgg bi nekk ci suufu 1.0 ak ñeneen ñi ñu nekk ci kaw 0 tuuti
    • Dafay dindi fonction perte
    • Dafay efaase klaas yu jaarul yoon
    • Dafay yokk lu tollu ci ñaari yoon limu jàng
  2. Benn valër buñ gëna xam ci parametru nooy epsilon mooy:
    • 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
    • AlfaGo ak AlfaZero
    • Tambali-v3 ak soppikat bi
  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. Lan mooy njuumte biñ bind ci nooy etiketu?
    • Saa yu nekk dafay wàññi njub
    • Mën na efaase nuru bu baax bi am ci diggante klaas yi, di gaañ distilaasioŋ xam-xam
    • Dafay laaj ñaari yoon done yiñ joxe ci tàggat yaram
    • Ci mbind kese lay dox
  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