Kediska Caadiga Lakabka

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Isku soo wada duuboo waa maxay caadiynta lakabku waxay xisaabisaa macnaha iyo kala duwanaanshaheeda?
   • Dhammaan sifooyinka hal tusaale
   • Dhammaan tusaalooyinka ku jira dufcadda-yar
   • Dhamaan miisaanka shabakada
   • Xilliyo kala duwan oo tababaro ah
2. Waa maxay sababta caadiga ah ee lakabka looga door biday caadi ka dhigista Dufcadaha ee Transformers?
   • Waxay u baahan tahay cabbir aad u weyn
   • Way ka madax bannaan tahay cabbirka dufcadda waxayna qabtaa taxanaha dhererka doorsoomayaasha
   • Waxay meesha ka saaraysaa baahida loo qabo wax kasta oo la baran karo
   • Waxa kaliya oo ay shaqeysaa inta lagu jiro wax-sheegid
3. Maxay yihiin cabbirrada la baran karo gamma iyo beta u oggolaadaan LayerNorm?
   • Dooro heerka waxbarashada
   • Deji tirada lakabyada
   • Dib u cabbir oo beddel wax soo saarka caadiga ah si ay shabakadu u soo ceshato matalaad waxtar leh
   • Ka saar baahida firfircoonida
4. Sidee RMSNorm uga duwan yahay heerka LayerNorm?
   • Waxay caadi ka dhigtaa dhammaan dufcaddii
   • Waxay isticmaashaa ma jirto wax xaddidan iyo qaybin
   • Waxay kaliya ku shaqeysaa sawirada
   • Waxay ka booddaa kala-goynta macnaheedu waa waxayna u qaybisaa oo keliya xidid-celcelis ahaan-square
5. Dhibaato noocee ah ayaa caadi ka dhigista lakabka ugu horrayn caawiyaa xallinta shabakadaha qoto dheer?
   • Dhaqdhaqaaqyada u socda miisaan aad u kala duwan, kuwaas oo carqaladeeya tababarka
   • Meesha diskooga oo gabaabsi ah
   • Doorashada xogta saxda ah
   • Sirta miisaanka modelka
6. Waa maxay sababta meelaynta 'caadiga ka hor' inta badan loogu isticmaalo transformers aad u qoto dheer?
   • Waxay ka dhigaysa moodelka mid yar
   • Caadiyan ka hor inta aan la soo koobin sublayer kasta ayaa ka dhigaysa xirmooyinka qoto dheer in ay sahlanaato oo aad u xasiloon si loo tababaro
   • Waxay meesha ka saartaa habka dareenka
   • Waxay si toos ah u labanlaabtaa heerka waxbarashada
7. Why is a small epsilon added to LayerNorm’s variance before taking its square root?
   • To make the batch size larger
   • To replace the learnable scale
   • To avoid division by zero and improve numerical stability
   • To compute the sequence length
8. If gamma is all ones and beta is all zeros, what does LayerNorm’s affine stage do?
   • It restores the original unnormalized inputs exactly
   • It applies a softmax over features
   • It changes the statistics to be batch-dependent
   • It leaves the normalized values unchanged after the mean-and-variance scaling