Kediska Dheecaan ee Gradient

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. In plain gradient descent, which direction is used relative to the objective's gradient?
   • The negative-gradient direction
   • The positive-gradient direction
   • An arbitrary perpendicular direction by definition
   • A direction chosen without evaluating any gradient
2. Muxuu xakameynayaa heerka waxbarashadu?
   • Tirada lakabyada qaabka
   • Immisa fasal ayaa tusaaluhu saadaalin karaa
   • Baaxadda tallaabo kasta oo la qaado inta lagu jiro tayaynta
   • Qadarka xogta tababarka ee la isticmaalay
3. How does a mini-batch gradient relate to the full selected training-data objective?
   • It uses no examples
   • It is computed on the batch and used as an estimate of the full-data gradient
   • It must equal the full-data gradient on every step
   • It only exists for images
4. Dhibaato noocee ah ayaa keeni karta heerka waxbarashada oo aad u weyn?
   • Tababarku wuxuu noqdaa mid aad u gaabis ah laakiin xasilloon
   • Qaabka ayaa iska indha tiraya jaanisyada
   • Xogta xogta waxay noqotaa mid khariban
   • Qaabku waxa uu ka batay inta ugu yar waxana laga yaabaa in uu kala duwanaado
5. What information does momentum carry into later gradient-descent updates?
   • Only the model's vocabulary size
   • A permanent deletion of all earlier gradients
   • A running weighted combination of earlier gradients
   • An unrelated random reset of every weight
6. Waa maxay sifada muhiimka ah ee hagaajinta Aadam marka la barbar dhigo farcanka cad?
   • Waxay la jaanqaadaysaa heerka waxbarasho ee waxtarka leh ee cabbir kasta
   • Waxay isticmaashaa hal tallaabo oo go'an oo cabbir kasta ah
   • Uma baahna gradients
   • Waxa kaliya oo ay tababartaa lakabka wax soo saarka
7. For plain gradient descent with old weight two, gradient three, and learning rate one-tenth, what is the new weight?
   • Two-point-three
   • One-point-nine-seven
   • Saddex
   • One-point-seven
8. What does a zero gradient fail to prove for a nonconvex training objective?
   • That the gradient value is zero at the evaluated point
   • That the current point is a global minimum
   • That the objective has been evaluated locally
   • That a stationary-point condition holds