Nesterov Yakawedzera Gradient Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. Ndeipi iyo inotsanangura pfungwa yeNesterov Yakawedzera Gradient ichienzaniswa neyechinyakare simba?
   • Inobvisa kukurumidza zvachose
   • Inoshandisa yakagadziriswa mwero wekudzidza we1
   • Iyo inoongorora gradient panzvimbo yekutarisa-mberi kwete chinzvimbo chiripo
   • Inongoshanda pasina mini-batches
2. Ndeipi chiyero chinogoneka chekuchinja chinoitwa neNesterov nzira pamatambudziko akatsetseka convex?
   • Odha 1/k^2
   • Odha 1/k
   • Odha 1/log k
   • Hapana chiyero chakavimbiswa
3. Ndiani pakutanga akaunza iyi yakakwidziridzwa gradient nzira?
   • Geoffrey Hinton muna 2012
   • Isaac Newton
   • John von Neumann
   • Yurii Nesterov muna 1983
4. Sei kutarira-mberi gradient ichibatsira pedyo neminima yakakombama?
   • Inowedzera mwero wekudzidza
   • Inofungidzira overshoot uye inoshandisa kururamisa zvisati zvaitika
   • Inobvisa izwi rekumhanya
   • Inoita randomizes nhanho nzira
5. Mukuita, iwo mutengo wekombuta weNesterov wekusimudzira unofananidzwa sei nekirasi yekusimudzira?
   • Zvakangofanana, nekuda kweiyo algebra yakarongwa patsva
   • Zvinenge gumi zvakapetwa kagumi
   • Zvinoda zvidimbu zvechipiri nhanho imwe neimwe
   • Haikwanise kuverengerwa paGPUs
6. Ndeipi inogadzirisa optimizer inosanganisa Nesterov kutarisa-mberi neAdhama-maitiro kuyera?
   • RMSprop
   • Adagrad
   • Nadam
   • LPFGS
7. Using the stated look-ahead form, theta = 10, learning rate = 0.1, beta = 0.9 and velocity = 2 give which evaluation point?
   • 10.18
   • 9.82
   • 8.20
   • 10.90
8. If beta is zero in the guide’s Nesterov look-ahead formula, where is the gradient evaluated?
   • At a point displaced by the full old velocity
   • At the previous validation score
   • At an arbitrary future minibatch
   • At the current parameter position