Maswali ya Kazi za Hasara

Majibu na maelezo huonekana unapojibu maswali.

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. Ni kazi gani ya upotezaji inayotumiwa sana kwa kazi za uainishaji?
   • Wastani wa hitilafu ya mraba
   • Inamaanisha kosa kabisa
   • Hasara ya msalaba-entropy
   • Umbali wa bawaba pekee
3. Ikilinganishwa na maana ya kosa la mraba, kwa nini unaweza kuchagua kosa kamili?
   • Huweka makosa ili kuwaadhibu zaidi
   • Ni thabiti zaidi kwa wauzaji wa nje kwa sababu haina makosa ya mraba
   • Haiwezi kutumika kwa urejeshaji
   • Inapuuza lebo za kweli
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. Kwa nini usahihi kawaida haitumiwi moja kwa moja kama upotezaji wa mafunzo?
   • Haiwezi kutofautishwa, kwa hivyo haitoi gradient muhimu
   • Ni rahisi sana kuhesabu
   • Inafanya kazi tu kwa regression
   • Daima ni sawa na hasara hata hivyo
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