Quiz ci fonction perte

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. For a prediction task, what does its selected loss quantify against the training target?
   • A specified prediction-error objective
   • Only runtime speed
   • Only the number of network layers
   • Every application benefit automatically
2. Ban fonction perte lañu gëna jëfandikoo ci liggéeyi xaaj?
   • Jumtukaay kaare moyen
   • Jumtukaay bu mat sëkk
   • Entropi bu jàkkarloo
   • Distance charnière kese
3. Buñu ko méngale ak njuumte kaare moyenne, lu tax nga tànn njuumte absolu moyenne?
   • Dafay kaare njuumte yi ngir gëna leen yar
   • Dafa gëna am doole ci outlier yi ndax du kaare njuumte yi
   • Mënu ñu ko jëfandikoo ngir régression
   • Dafay baña bàyyi xel ci etiketu dëgg yi
4. Why does gradient-based training need a usable loss derivative or suitable substitute?
   • So a loss number can be printed
   • So all learning methods become identical
   • So the dataset no longer needs targets
   • So backpropagation and optimization can obtain an update signal
5. How does one-hot class cross-entropy change as probability assigned to the target class becomes very small?
   • Its loss must become zero
   • It rewards the prediction increasingly
   • Its loss becomes large
   • It becomes identical to accuracy
6. Lan moo tax duñu faral di jëfandikoo njub directement ni perte de formation?
   • Duñu ko mëna wuutale, moo tax du joxe benn gradient bu am njariñ
   • Yomb naa xayma lool
   • Regression rekk lay dox
   • Saa yu nekk dafay méngoo ak ñàkk
7. For illustrative regression residuals one and three, what are mean squared error and mean absolute error?
   • MSE is two and MAE is five
   • Both are four
   • MSE is ten and MAE is four
   • MSE is five and MAE is two
8. Using a base-two logarithm, what one-hot cross-entropy loss corresponds to target-class probability one-quarter?
   • One-quarter bit
   • Two bits
   • Four bits
   • Zero bits