Kuiz berkaitan panduan · Sederhana Tahap

Kuiz Melicinkan Label

Meliputi sasaran terlicin dan epsilon, kesan penentukuran bergantung kepada tugas, tukar ganti penyulingan, dan sebab keputusan bergantung pada data dan objektif.

Laluan panduan yang berkaitanMelicinkan Label
soalan 1 daripada 8

Apakah perubahan pelicinan label tentang sasaran latihan?

Pratonton setiap soalan8 soalan

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

  1. Apakah perubahan pelicinan label tentang sasaran latihan?
    • Ia melembutkan sasaran satu panas supaya kelas sebenar berada di bawah 1.0 dan yang lain sedikit di atas 0
    • Ia menghilangkan fungsi kehilangan
    • Ia memadamkan kelas yang salah
    • Ia menggandakan kadar pembelajaran
  2. Nilai biasa untuk epsilon parameter pelicinan ialah:
    • 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 dan AlphaZero
    • Inception-v3 dan 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. Apakah kelemahan yang didokumenkan bagi pelicinan label?
    • Ia sentiasa mengurangkan ketepatan
    • Ia boleh memadamkan persamaan halus antara kelas, menjejaskan penyulingan pengetahuan
    • Ia memerlukan dua kali ganda data latihan
    • Ia hanya berfungsi pada teks
  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