Cuestionario vinculado a una guía · Medio Nivel

Prueba de retropropagación

Pruebe gradientes de retropropagación, orden de dependencia inverso, valores directos almacenados en caché, multiplicación de reglas de cadena, sumas de rutas compartidas y separación de optimizadores.

Rutas de guía relacionadasPropagación hacia atrás
Pregunta 1 de 8

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

Vista previa de cada pregunta8 preguntas

Las respuestas y explicaciones aparecen a medida que realiza el cuestionario.

  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. ¿Qué regla matemática está en el centro de la propagación hacia atrás?
    • El teorema de Pitágoras
    • teorema de bayes
    • La regla de la cadena del cálculo.
    • La fórmula cuadrática
  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. ¿En qué orden la retropropagación calcula los gradientes?
    • Desde la capa de entrada hacia la capa de salida
    • Todas las capas simultáneamente sin orden.
    • Sólo para la capa oculta intermedia
    • Desde la capa de salida hacia atrás hacia la capa 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?
    • siete
    • uno
    • Three quarters
    • Doce
  8. A shared parameter has loss-gradient contributions two and five through two paths. What combined contribution is accumulated?
    • diez
    • siete
    • tres
    • Two fifths