Adanwo Awọn iṣẹ Isonu

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

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. Iṣẹ ipadanu wo ni a lo julọ fun awọn iṣẹ ṣiṣe isọdi?
   • Aṣiṣe onigun mẹrin tumọ si
   • Itumọ aṣiṣe pipe
   • Cross-entropy pipadanu
   • Ijinna mitari nikan
3. Ti a ṣe afiwe si tumọ si aṣiṣe onigun mẹrin, kilode ti o le yan tumọ si aṣiṣe pipe?
   • O ṣe iyipo awọn aṣiṣe lati jẹ wọn ni iya diẹ sii
   • O ti wa ni diẹ logan to outliers nitori ti o ko ni square awọn aṣiṣe
   • Ko le ṣee lo fun ipadasẹhin
   • O foju awọn aami otitọ
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. Kini idi ti deede kii ṣe lo taara bi pipadanu ikẹkọ?
   • Ko ṣe iyatọ, nitorinaa ko fun gradient ti o wulo
   • O rọrun pupọ lati ṣe iṣiro
   • O ṣiṣẹ nikan fun ipadasẹhin
   • O nigbagbogbo dogba pipadanu naa lonakona
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