Ikibazo gihuza ibibazo · Hagati Urwego
Ikibazo cya Backpropagation
Gerageza gusubiza inyuma gradients, guhinduranya kwishingikirizaho, gutondekanya imbere indangagaciro, urunigi-amategeko kugwiza, gusangira-inzira amafaranga, hamwe no gutandukanya optimizer.
Ikibazo 1 Bya 8
What quantity does backpropagation compute for a neural network's relevant weights?
Reba buri kibazo8 ibibazo
Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.
- 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
- Ni irihe tegeko ry'imibare riri mu mutima wo gusubira inyuma?
- Inyigisho ya Pythagorean
- Bayes 'theorem
- Amategeko y'urunigi rwo kubara
- Inzira ya kane
- 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
- Ni mu buhe buryo gusubira inyuma bibara gradients?
- Kuva mubyinjijwe byerekeza kubisohoka
- Inzego zose icyarimwe nta gahunda
- Gusa kuri hagati rwihishe
- Uhereye kubisohoka bisubira inyuma ugana ibyinjira
- 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?
- Birindwi
- Imwe
- Three quarters
- Twelve
- A shared parameter has loss-gradient contributions two and five through two paths. What combined contribution is accumulated?
- Icumi
- Birindwi
- Bitatu
- Two fifths