Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska Shabakadda Neural-ka ee Convolutional

Tijaabi kernels CNN-ka ee la wadaago, hoos u dhigista boosaska, kala sarraynta sifada la bartay, taariikhda AlexNet, xisaabinta wax soo saarka, iyo daboolida kanaalka-gelinta cufan.

Wadooyinka haga ee la xidhiidhaIsku xirka Neural Networks
Su'aal 1 ee 8

Waa maxay shaqada ugu weyn ee shaandhada (kernel) ee CNN?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Waa maxay shaqada ugu weyn ee shaandhada (kernel) ee CNN?
    • Si loo kaydiyo summada kala soocidda u dambaysa
    • Si aan kala sooc lahayn isku shaandheyn pixels ka hor tababarka
    • Si aad u dul-maro sawirka oo aad u ogaato qaab muuqaal gaar ah
    • Si sawirka loogu badalo maqal
  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. CNN qoto dheer, sidee ayay astaamuhu guud ahaan uga beddelaan lakabyada hore ilaa lakabyada dambe?
    • Laga soo bilaabo walxaha oo dhan ilaa hal pixels
    • Lakab walba way isku mid yihiin
    • Laga bilaabo qoraalka ilaa nambarada kaliya
    • Laga soo bilaabo geesaha fudud iyo midabada ilaa qaybo kakan sida indhaha ama giraangiraha
  5. Which named CNN is associated with the influential 2012 ImageNet classification result?
    • AlexNet
    • ResNet
    • Vision Transformer
    • SqueezeNet
  6. Waa maxay hawlgalka tirada dhacaya marka shaandhada lagu dhejiyo balastar sawirka?
    • pixels-yada waxaa laga soocay kuwa ugu madow ilaa kuwa ugu iftiimaya
    • balastarkii waa laga tirtiray sawirka
    • Miisaan kasta waxaa lagu dhuftaa pixels is dulsaaran, alaabooyinkana waa la soo koobay
    • pixels waxa loo rogaa xarfo
  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