Tete idekun adanwo

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

1. Ifihan agbara wo ni idaduro ni kutukutu ṣe atẹle akọkọ lati pinnu igba lati da duro?
   • Afọwọsi-ṣeto išẹ
   • Idasonu ikẹkọ-ṣeto
   • GPU otutu
   • Nọmba ti paramita awoṣe
2. Kini iṣakoso paramita 'suuru'?
   • Iwọn ẹkọ ti o pọju
   • Awọn akoko melo ni lati duro laisi ilọsiwaju ṣaaju idaduro
   • Iwọn ipele naa
   • Awọn nọmba ti afọwọsi agbo
3. Lẹhin awọn okunfa idaduro ni kutukutu, awọn iwọn wo ni o yẹ ki o tọju nigbagbogbo?
   • Awọn òṣuwọn lati ik epoch
   • Awọn iwuwo ibẹrẹ laileto
   • Awọn òṣuwọn lati awọn ti o dara ju afọwọsi epoch
   • Awọn apapọ ti gbogbo epochs
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. Apẹrẹ aṣoju ti ifọwọsi-aṣiṣe aṣiṣe lakoko ikẹkọ jẹ apejuwe ti o dara julọ bi:
   • A U-apẹrẹ ti o ṣubu lẹhinna dide
   • monotonically dinku
   • A alapin ila
   • monotonically npo si
6. Kí ni ‘min_delta’ àbáwọlé sábà máa ń tọ́ka sí?
   • Awọn kere nọmba ti fẹlẹfẹlẹ
   • Ilọsiwaju ti o kere julọ ti o ka bi ilọsiwaju
   • Iwọn ipele ti o kere julọ
   • Iwọn ipilẹ data to kere julọ
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