Kedis ku xidhan hagaha · Fudud Heerka

Kediska Joogsiga Hore

Waxay dabooshaa la socodka ansaxinta, dulqaadka iyo soo kabashada barta kontaroolada, iyo marka hore ee joojinta waxay joogtayn kartaa tababarka iyada oo aan dammaanad qaadin qaladka imtixaanka hoose.

Wadooyinka haga ee la xidhiidhaJoogsi hore
Su'aal 1 ee 8

Calaamadee goor hore joojinta marka hore la socota si loo go'aamiyo goorta la joojinayo?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Calaamadee goor hore joojinta marka hore la socota si loo go'aamiyo goorta la joojinayo?
    • Waxqabadka la dejiyay ee ansixinta
    • lumitaanka tababarka
    • heerkulka GPU
    • Tirada cabbiraadaha moodeelka
  2. Muxuu xakameynayaa cabbirka 'sabirka'?
    • Heerka waxbarasho ee ugu badan
    • Immisa xilli ayaa la sugi doonaa iyada oo aan la hagaajin ka hor inta aan la joojin
    • Cabbirka dufcadda
    • Tirada isku laabma ansixinta
  3. Ka dib joojinta hore ee kicinta, miisaankee ayaad caadi ahaan ilaalinaysaa?
    • Miisaanka laga soo bilaabo xilligii ugu dambeeyay
    • Miisaanka si aan kala sooc lahayn loo bilaabay
    • Miisaanka laga soo bilaabo xilligii ansixinta ugu fiicnaa
    • Celceliska dhammaan xilliyadii
  4. Why can early stopping act as a form of regularization?
    • It adds a fixed L2 penalty to every weight
    • It guarantees lower test error on every dataset
    • It prevents the model from seeing training examples
    • It limits how long optimization proceeds and can reduce fitting to training-specific patterns
  5. Qaabka caadiga ah ee qalooca ansaxinta-qalada inta lagu jiro tababarka waxaa sida ugu wanaagsan loogu sifeeyay sida:
    • Qaab-u-qaab ah oo soo dhacaya ayaa markaa kaca
    • Keli ahaan hoos u dhacaya
    • Xariiq fidsan
    • monotonically u kordhaya
  6. Waa maxay heerka 'min_delta' caadi ahaan qeexayaa?
    • Tirada ugu yar ee lakabyada
    • Horumarka ugu yar ee lagu tiriyo horumarka
    • Cabbirka dufcadda ugu yar
    • Cabbirka xogta ugu yar
  7. What does patience allow an early-stopping rule to do?
    • Continue training forever regardless of validation results
    • Change the model architecture after every batch
    • Wait through a set number of validation checks without qualifying improvement before stopping
    • Use the test set to select the final epoch
  8. Why should the test set generally remain outside the early-stopping loop?
    • The test set cannot contain labels
    • Training libraries cannot load test data
    • Early stopping requires the test set to be empty
    • Repeatedly selecting by test performance would make it part of model selection