Guide-yakabatana mibvunzo · Pakati Nhanho

Backpropagation Quiz

Edzai backpropagation gradients, reverse dependency order, cached forward values, cheni-mutemo kuwanda, akagovaniswa-nzira sums, uye optimizer kupatsanurwa.

Nzira dzekutungamira dzinoenderanaKudzokera kumashure
Mubvunzo 1 ye 8

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

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  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. Ndeupi mutemo wemasvomhu uri pamwoyo wekudzokera shure?
    • Theorem yePythagorean
    • Theorem yeBayes
    • Mutemo wechain of calculus
    • Iyo quadratic formula
  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. Ndekupi kurongeka uko kudzoreredzwa kunoverengera gradients?
    • Kubva pane yekupinza yakananga kune yekubuda layer
    • All layers panguva imwe chete pasina kurongeka
    • Chete chepakati chakavanzika layer
    • Kubva pane yakabuda layer ichidzokera kumashure yakananga kune yekupinza layer
  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?
    • Nomwe
    • Imwe
    • Three quarters
    • Twelve
  8. A shared parameter has loss-gradient contributions two and five through two paths. What combined contribution is accumulated?
    • Gumi
    • Nomwe
    • Vatatu
    • Two fifths