Saamaynta Hawlaha Tababarka Xogta Kediska

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay su'aasha ka-hortagga ah ee saameeya shaqooyinka qiyaas ahaan?
   • Sida khasaaraha goobta imtixaanku u bedeli lahaa haddii tusaalaha tababarka meesha laga saaro ama kor loo qaado
   • Sida saxda ah ee moodalku waa celcelis ahaan
   • Intee in le'eg ayuu modelku tareen
   • Immisa halbeeg ayaa moodelku leeyahay
2. Shayga xisaabeed ee ka dhigaya xisaabinta saamaynta saxda ah mid aan la qabsan karin moodooyinka waaweyn?
   • Shaqada softmax
   • Hessian rogan ee khasaaraha
   • Jadwalka heerka waxbarashada
   • Cabbirka dufcadda
3. Yaa la qabsaday hawlaha saamaynta barashada qoto dheer ee casriga ah ee warqadda 2017 ee caanka ah?
   • Goodfellow iyo Bengio
   • Vaswani iyo al.
   • Koh iyo Liang
   • Hinton iyo LeCun
4. Under Koh and Liang’s standard I_up,loss convention, what does a negative value indicate?
   • The point was not in the training data
   • Upweighting the point is estimated to increase test loss
   • The point has no relationship to the test example
   • Upweighting the point is estimated to lower test loss, so it is helpful
5. Qiyaastee ayay Anthropic u isticmaashay si loo cabbiro saamaynta hawlaha luuqadaha waaweyn?
   • EK-FAC (curvature-ka-Kronecker-ka leh)
   • Ka saarida
   • Baadhitaanka Beam
   • Isku qas
6. Maxay Anthropic ka heshay daraasadda la miisaamay ee ku saabsan tusaalooyinka saamaynta leh?
   • Had iyo jeer waa nuqullo sax ah oo wax soo saarka ah
   • Waxay inta badan wadaagaan qaabab aan la taaban karin halkii ay ka ahaan lahaayeen ereyo isku mid ah
   • Si aan kala sooc lahayn ayaa loo qaybiyaa
   • Kaliya tusaalaha tababarka ugu horreeya ayaa muhiim ah
7. In the influence-function approximation, what connects a training-example gradient to the effect on a test loss?
   • The test set’s token count
   • A random forest over training labels
   • The inverse Hessian of the training loss
   • The model’s output vocabulary size
8. If removing one training example is estimated to increase a test point’s loss, what does that suggest about the example?
   • It was guaranteed to be a duplicate
   • It had no relationship to the model
   • It necessarily caused the model to overfit
   • It had a helpful influence on that test point under the approximation