Ikibazo gihuza ibibazo · Hagati Urwego

Akarango Korohereza Ikibazo

Igipfukisho cyoroheje intego na epsilon, ingaruka zishingiye kubikorwa bya kalibrasi, kugurisha ibicuruzwa, n'impamvu ibisubizo biterwa namakuru n'intego.

Inzira zijyanye no kuyoboraAkarango Korohereza
Ikibazo 1 Bya 8

Niki ikirango cyoroshya gihindura intego zamahugurwa?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Niki ikirango cyoroshya gihindura intego zamahugurwa?
    • Yoroshya intego imwe ishyushye kuburyo urwego rwukuri ruri munsi ya 1.0 naho abandi bari hejuru ya 0
    • Ikuraho imikorere yigihombo
    • Isiba ibyiciro bitari byo
    • Bikubye kabiri igipimo cyo kwiga
  2. Agaciro gasanzwe kubintu byoroshye epsilon ni:
    • 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 na AlphaZero
    • Intangiriro-v3 na Transformer
  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. Niki cyanditse nabi cyerekana label yoroshye?
    • Buri gihe bigabanya ukuri
    • Irashobora guhanagura neza hagati y-amasomo asa, bikomeretsa ubumenyi
    • Birasaba kabiri amakuru yamahugurwa
    • Ikora gusa ku nyandiko
  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