Guide-yakabatana mibvunzo · Pakati Nhanho

Label Smoothing Quiz

Inovhara zvibodzwa zvakatsetseka uye epsilon, basa rinotsamira calibration mhedzisiro, distillation tradeoffs, uye nei mhedzisiro inoenderana nedata uye chinangwa.

Nzira dzekutungamira dzinoenderanaKunyorovesa Mavara
Mubvunzo 1 ye 8

Chii chinoshandura label smoothing pamusoro pezvinangwa zvekudzidzisa?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Chii chinoshandura label smoothing pamusoro pezvinangwa zvekudzidzisa?
    • Iyo inopfavisa-imwe-inopisa zvibodzwa kuitira kuti kirasi yechokwadi ive pazasi 1.0 uye mamwe ari pamusoro zvishoma
    • Inobvisa basa rekurasikirwa
    • Inobvisa makirasi asiri iwo
    • Inopeta kaviri mwero wekudzidza
  2. Yakajairika kukosha kweiyo inotsvedza paramende epsilon ndeiyi:
    • 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 uye AlphaZero
    • Kutanga-v3 uye 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. Chii chinonzi downside yelabel smoothing?
    • Nguva dzose inoderedza kururama
    • Inogona kudzima yakanaka pakati-yekirasi kufanana, kukuvadza ruzivo distillation
    • Inoda kaviri data yekudzidziswa
    • Inoshanda chete pane zvinyorwa
  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