Sharpness-Aware Minimization Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. Ndeupi rudzi rwehushoma hunoyedzwa neSAM kuwana?
   • A flat minimum apo kurasikirwa kunogara kwakaderera munzvimbo yehuremu
   • Iyo inopinza inogoneka shoma
   • Iyo shoma ine yakawanda parameters
   • Chero hushoma hunosvikika munhanho imwe
2. Mangani ekumberi-kumashure anopfuura anodiwa nhanho yeSAM yakajairwa?
   • Half pass
   • Zvinenge zviviri
   • Imwe chete
   • Gumi kana kupfuura
3. Chii chinonzi radius hyperparameter rho control muSAM?
   • The kudzidza mwero kuora kukurumidza
   • Huwandu hwenguva dzekudzidziswa
   • Saizi yenharaunda yakatenderedza huremu iyo inodzivirirwa kubva pakurasikirwa nemaspikes
   • The dropout mukana
4. Ndeipi yekutanga nhanho mbiri dzeSAM pakudzokorora kwega kwega?
   • Deredza muenzaniso
   • Avhareji yehuremu hwematanho ese apfuura
   • Reset the optimizer state
   • Tora nhanho yekukwira yehukuru rho wakananga kune yakaipisisa-kesi iri padyo nzvimbo
5. Sei SAM ichiwanzovandudza kusimba kuisa ruzha?
   • Nekuti flat minima hainyanyi kubata nemusoro mavara akaora
   • Nekuti inodzima zvinyorwa zvine ruzha zvoga
   • Nokuti rinoshandisa mashoko makuru
   • Nekuti inowedzera katatu saizi yebatch
6. Ndeupi weiyi musiyano wakagadzirirwa kudzikisa mutengo wemakomputa weSAM?
   • ReLU
   • ESAM (SAM Inoshanda)
   • BatchNorm
   • 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