quiz bu lëkkale ak tegtal · Diggante Niveau

Laajte ci Reseau Neuraal Konvolusionel

Test kernel CNN yiñ séddoo, wàññi sampling spatial, hierarchie man-man yiñ jàng, jaar-jaaru AlexNet, xayma yi ci griy biy génne, ak coverage bu dëgër ci chaine yi.

Yooni njiit yu jëm ciReseau neuronal konvolusionel
Laaj 1 de 8

Lan mooy liggéeyu filtre (kernel) ci CNN?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Lan mooy liggéeyu filtre (kernel) ci CNN?
    • Ngir denc etiketu xaaj bu mujj bi
    • ngir jaxase pixel yi ci anam wu mucc balaa ngay tàggat
    • Ngir gliise ci biir nataal bi nga gis benn motif buñ mëna gis
    • Ngir soppi nataal bi def ko audio
  2. How does spatial kernel sharing reduce parameter requirements compared with learning a separate kernel at every image location?
    • The same learned kernel weights are reused across locations
    • All input pixels are deleted
    • Every layer must use only grayscale data
    • The model avoids all training
  3. What does a spatial pooling layer commonly do to a CNN feature map?
    • Assign a final label to every object
    • Reduce its spatial resolution
    • Guarantee invariance to every possible image shift
    • Always increase the number of input channels
  4. Ci CNN bu xóot bi, naka la man-man yi di soppikoo ci layer yu njëkk yi dem ci layer yu ci topp yi?
    • Liko dalee ci mbir yépp dem ba ci benn pixel
    • Dañuy wéy di nuru ci bépp etaas
    • Liko dalee ci bind dem ci nimero kese
    • Liko dalee ci catu boor yi ak melo yi ba ci wàll yu jafee xam yu melni bët yi wala pëno yi
  5. Which named CNN is associated with the influential 2012 ImageNet classification result?
    • AlexNet
    • Resnet
    • Vision Transformer
    • SqueezeNet
  6. Ban jëf numérik mooy am suñu defee filtre ci benn patch ci nataal bi?
    • Pixel yi dañu leen tànn di tàmbalee ci li gëna ñuul ba ci li gëna leer
    • Dañu efaase patch bi ci nataal bi
    • Diisaay bu nekk dañu koy yokk ci pixel bi ciy jaxasoo, ba noppi ñu boole produit yi
    • Pixel yi dañu leen di soppi def ay araf
  7. With a 6-by-6 input and 3-by-3 kernel at stride one, no padding, and no dilation, what is the CNN output-grid size?
    • 6 by 6
    • 3 by 3
    • 2 by 2
    • 4 by 4
  8. In dense ungrouped convolution on a three-channel input, which channels does one filter span?
    • Only the first channel by definition
    • All three input channels
    • No input channels because kernels contain only output labels
    • Exactly one channel in every convolution configuration