Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo cyo Gutakaza Ikibazo

Intego yo guhanura ibizamini, amakosa aringaniye kandi yuzuye, ibyiciro byambukiranya-entropiya, ibikoreshwa mumahugurwa akoreshwa, ibice byigihombo, hamwe nimpuzandengo yibibazo.

Inzira zijyanye no kuyoboraGutakaza Imikorere
Ikibazo 1 Bya 8

For a prediction task, what does its selected loss quantify against the training target?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  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. Nibihe bikorwa byo gutakaza bikoreshwa cyane mubikorwa byo gutondeka?
    • Ikigereranyo cya kare
    • Sobanura ikosa ryuzuye
    • Igihombo cya cross-entropy
    • Intera ya Hinge gusa
  3. Ugereranije no gusobanura ikosa, kuki ushobora guhitamo gusobanura ikosa ryuzuye?
    • Irahuza amakosa yo kubahana byinshi
    • Birakomeye cyane kubasohoka kuko ntabwo ari amakosa ya kare
    • Ntishobora gukoreshwa mugusubira inyuma
    • Irengagiza ibirango nyabyo
  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. Ni ukubera iki ubusanzwe budakoreshwa neza nko gutakaza imyitozo?
    • Ntabwo itandukanye, ntabwo rero itanga ingirakamaro
    • Biroroshye cyane kubara
    • Ikora gusa kugirango isubire inyuma
    • Burigihe bingana nigihombo uko byagenda kose
  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