Kuiz berkaitan panduan · Keras Tahap

VC Dimension and PAC Learning Quiz

Tests shattering, VC dimension, agnostic PAC sample complexity, and why worst-case guarantees can be looser than observed model performance.

Laluan panduan yang berkaitanVc Dimension And Pac Learning
soalan 1 daripada 8

Untuk tiga titik dapat dipecahkan oleh kelas hipotesis binari, apa yang mesti dapat dilakukan oleh kelas tersebut?

Pratonton setiap soalan8 soalan

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

  1. Untuk tiga titik dapat dipecahkan oleh kelas hipotesis binari, apa yang mesti dapat dilakukan oleh kelas tersebut?
    • The class can correctly classify all n points on unseen test data
    • The class contains exactly n hypotheses
    • The points are linearly separable by exactly one hypothesis
    • For every one of the 2^n possible labelings of those points, some hypothesis in the class reproduces it exactly
  2. Bagi penapis binari garis lurus dalam satah dua dimensi, berapa banyak titik paling banyak yang boleh dipecahkan?
    • 1
    • 3
    • 2
    • 4
  3. Dalam tetapan agnostik PAC yang diterangkan dalam panduan, bagaimana batas sampel kes terburuk standard bergantung pada dimensi VC dan epsilon?
    • Sample size needed scales roughly with VC-dimension divided by epsilon squared
    • Sample size needed decreases as VC dimension increases
    • Sample size needed is independent of VC dimension
    • Sample size needed depends only on the number of features, never on VC dimension
  4. Mengapa pengklasifikasi satu ambang pada garis nyata dikatakan mempunyai dimensi VC 1?
    • It has one parameter, t, so its VC dimension equals its parameter count
    • It can only classify positive examples
    • It can shatter exactly one point but not every arrangement of two points
    • It has an infinite VC dimension since t can be any real number
  5. Adakah dimensi VC sama dengan bilangan parameter dalam model, menurut panduan?
    • Yes, they are always identical
    • Yes, but only for linear models
    • No, VC dimension only applies to neural networks
    • No; some infinite-parameter classes have finite VC dimension and some low-parameter models can have high VC dimension
  6. What theoretical result explains why the growth function becomes only polynomial in n once n exceeds the VC dimension?
    • Sauer's lemma
    • Teorem had pusat
    • Teorem Bayes
    • Hukum bilangan besar
  7. Why do classical VC-dimension-based PAC bounds struggle to explain deep neural network generalization?
    • Neural networks have zero VC dimension
    • PAC theory does not apply to any parametric models
    • Neural networks' VC dimension is often far larger than practical training set sizes, yet they still generalize well
    • Neural networks cannot be represented as hypothesis classes
  8. What kind of guarantee does PAC learning provide about a learned hypothesis?
    • That it will have exactly zero error
    • That with high probability its error is within some epsilon of the best hypothesis in the class
    • That it will always outperform every other hypothesis class
    • That it requires no training data at all