Útmutatóhoz kapcsolódó kvíz · Közepes Szint
Visszaterjesztési kvíz
Test backpropagation gradients, reverse dependency order, cached forward values, chain-rule multiplication, shared-path sums, and optimizer separation.
kérdés 1 -ból 8
What quantity does backpropagation compute for a neural network's relevant weights?
Tekintse meg az összes kérdést8 kérdéseket
A válaszok és magyarázatok megjelennek a kvíz kitöltésekor.
- 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
- Melyik matematikai szabály áll a visszaterjesztés középpontjában?
- A Pitagorasz-tétel
- Bayes tétele
- A kalkulus láncszabálya
- A másodfokú képlet
- 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
- Milyen sorrendben számítja ki a visszaszaporítás a színátmeneteket?
- A bemeneti rétegtől a kimeneti réteg felé
- Minden réteg egyszerre, sorrend nélkül
- Csak a középső rejtett réteghez
- A kimeneti rétegtől visszafelé a bemeneti réteg felé
- 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
- 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
- On one composed backpropagation path, local scalar derivatives are three and four. What is their chain-rule product?
- Hét
- Egy
- Three quarters
- Twelve
- A shared parameter has loss-gradient contributions two and five through two paths. What combined contribution is accumulated?
- Tíz
- Hét
- Három
- Two fifths