Questionário vinculado ao guia · Médio Nível

Questionário de retropropagação

Teste gradientes de retropropagação, ordem de dependência reversa, valores de encaminhamento em cache, multiplicação de regras de cadeia, somas de caminho compartilhado e separação de otimizador.

Caminhos de guia relacionadosRetropropagação
Pergunta 1 de 8

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

Visualize cada pergunta8 perguntas

As respostas e explicações aparecem conforme você responde ao teste.

  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. Qual regra matemática está no cerne da retropropagação?
    • O teorema de Pitágoras
    • Teorema de Bayes
    • A regra da cadeia do cálculo
    • A fórmula quadrática
  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. Em que ordem a retropropagação calcula gradientes?
    • Da camada de entrada em direção à camada de saída
    • Todas as camadas simultaneamente sem ordem
    • Apenas para a camada oculta do meio
    • Da camada de saída para trás em direção à camada de entrada
  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?
    • Sete
    • Um
    • Three quarters
    • Twelve
  8. A shared parameter has loss-gradient contributions two and five through two paths. What combined contribution is accumulated?
    • Dez
    • Sete
    • Três
    • Two fifths