Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska Hawlaha Luminta

Tijaabi ujeedooyinka saadaasha, khaladaad labajibaaran iyo khaladaad buuxa, fasalka iskutallaabta, noocyada tababarka la isticmaali karo, unugyada khasaaraha, iyo celceliska khaladaadka nambarada.

Wadooyinka haga ee la xidhiidhaHawlaha Luminta
Su'aal 1 ee 8

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

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  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. Waa maxay shaqada khasaaraha inta badan loo isticmaalo hawlaha kala soocidda?
    • Khalad afar gees leh celcelis ahaan
    • Macnaha qalad buuxa
    • Luminta-entropy
    • Masaafada luqunta kaliya
  3. Marka la barbar dhigo macnaha khalad labajibbaaran, maxaad u dooran kartaa qalad buuxa?
    • Waxay dib u dhigtaa khaladaadka si ay u ciqaabto in ka badan
    • Way ka sii adag tahay kuwa ka baxsan sababtoo ah ma laba jibaarto khaladaadka
    • Looma isticmaali karo dib u soo noqoshada
    • Waxay iska indha tirtaa sumadaha runta ah
  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. Waa maxay sababta saxnaanta inta badan aan si toos ah loogu isticmaalin luminta tababarka?
    • Ma aha mid la kala sooci karo, sidaas darteed ma siinayso gradient faa'iido leh
    • Aad bay u fududahay in la xisaabiyo
    • Waxay kaliya u shaqeysaa dib u noqoshada
    • Had iyo jeer waxay la mid tahay khasaaraha si kastaba
  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