Kuiz berkaitan panduan · Sederhana Tahap

Kuiz Rambatan Belakang

Uji kecerunan perambatan belakang, tertib pergantungan terbalik, nilai ke hadapan yang dicache, pendaraban peraturan rantai, jumlah laluan kongsi dan pemisahan pengoptimum.

Laluan panduan yang berkaitanPenyebaran balik
soalan 1 daripada 8

What quantity does backpropagation compute for a neural network's relevant weights?

Pratonton setiap soalan8 soalan

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

  1. What quantity does backpropagation compute for a neural network's relevant weights?
    • Derivatives of the loss with respect to those weights
    • A causal percentage of total error uniquely assigned to each weight
    • The architecture drawing without any calculation
    • A permanently updated set of weights without an optimizer
  2. Peraturan matematik manakah yang menjadi teras kepada perambatan balik?
    • Teorem Pythagoras
    • Teorem Bayes
    • Peraturan rantaian kalkulus
    • Formula kuadratik
  3. Why can reverse-mode backpropagation compute many parameter derivatives efficiently?
    • It avoids all local derivatives
    • It reuses graph structure and relevant intermediate results
    • It calculates only the output prediction again
    • It guarantees every implementation has exactly one forward pass of runtime
  4. Dalam susunan apakah rambatan belakang mengira kecerunan?
    • Dari lapisan input ke arah lapisan output
    • Semua lapisan serentak tanpa susunan
    • Hanya untuk lapisan tersembunyi tengah
    • Dari lapisan keluaran ke belakang ke arah lapisan input
  5. Does computing backpropagation gradients by itself establish that model weights were updated?
    • Yes; every backward computation automatically applies a learning rate
    • Yes; gradient values always replace the weights directly
    • No; the optimizer update is a separate step
    • Only if the network has no parameters
  6. In a conventional cached-backpropagation workflow, what does the forward computation provide for later derivative calculations?
    • Relevant intermediate values that can be retained for the backward computation
    • A completed optimizer update without any update rule
    • A guarantee that all later evaluation errors disappear
    • A permanent deletion of the training objective
  7. On one composed backpropagation path, local scalar derivatives are three and four. What is their chain-rule product?
    • Tujuh
    • satu
    • Three quarters
    • Dua belas
  8. A shared parameter has loss-gradient contributions two and five through two paths. What combined contribution is accumulated?
    • Sepuluh
    • Tujuh
    • Tiga
    • Two fifths