Quiz buy wàññi ñaw

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Ban xeetu minimum la SAM di jéema gis?
   • Minimum bu plat fu perte bi di gëna néew ci dëkkandoo yi
   • Minimum bi gëna ñaw
   • Minimum bi am parametre yu bari
   • Bépp minimum buñu mëna yegg ci benn jéego
2. Ñaata paas ci kanam ak ci ginaaw la jéego SAM buñ miin di soxla?
   • Genn-wàll paas
   • Lu tollu ci ñaar
   • Benn
   • Fukk wala lu ëpp
3. Lan la hiperparametru rayon rho di saytu ci SAM?
   • Gaawaayu decay bi ci jàng
   • limu jamonoy tàggat yaram
   • Dayo dëkkandoo yi wër poid yi ñuy aar ci piques perte
   • Waajalug bàyyi jàngi
4. Lan mooy li njëkk ci ñaari jéego yi SAM wara def ci iteration bu nekk?
   • Wàññil model bi
   • Moyenne poids jéego yi weesu yépp
   • Delloosi staadu optimisatër bi
   • Defal ab jéego bu tollu ci rho ngir yegg ci barab bi gëna bon
5. Lu tax SAM di faral di gëna dëgëral etiketu bruit yi?
   • Ndax minima yu plat yi ñoo gëna néew luñu mëna xam etiket yu yàqu yi
   • Ndax dafay efaase ci saasi etiketu bruit yi
   • Ndax dafay jëfandikoo vocabulaire bu gëna bari
   • Ndax dafay yokk lu tollu ci ñetti yoon
6. Ci yii, yan ci ñoom mooy anam biñ defar ngir wàññi njëgu ordinatëru SAM?
   • ReLU
   • ESAM (SAM bu baax)
   • Norm de lote
   • AdaGrad
7. In SAM’s second pass, which gradient is used to update the original model weights?
   • The gradient of a random label
   • The first pass gradient without evaluating the perturbed point
   • The gradient evaluated at the perturbed nearby weights
   • A gradient from a different model checkpoint
8. If SAM’s neighborhood radius rho is set to zero, what happens to its perturbation step?
   • The model parameters are all set to zero
   • The loss becomes independent of the weights
   • The optimizer takes an infinite step
   • There is no weight perturbation, so the neighborhood reduces to the current point