Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo cyemewe cya Neural Network Quiz

Ikizamini gisangiwe na CNN intungamubiri, ahantu hatagaragara, wize ibiranga urwego, amateka ya AlexNet, kubara-grid kubara, hamwe no kwinjiza-umuyoboro wuzuye.

Inzira zijyanye no kuyoboraImiyoboro ya Neural Network
Ikibazo 1 Bya 8

Nuwuhe murimo wingenzi wa filteri (intangiriro) muri CNN?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Nuwuhe murimo wingenzi wa filteri (intangiriro) muri CNN?
    • Kubika ikirango cyanyuma
    • Guhinduranya kuri pigiseli mbere yo kwitoza
    • Kunyerera hejuru yishusho no kumenya uburyo bwihariye bwo kubona
    • Guhindura ishusho mumajwi
  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. Muri CNN yimbitse, ni gute ibintu bisanzwe bihinduka kuva mubyiciro byambere bikagera kumurongo?
    • Kuva mubintu byose kugeza kuri pigiseli imwe
    • Ziguma zisa kuri buri cyiciro
    • Kuva ku nyandiko kugeza ku mibare gusa
    • Kuva kumpande zoroshye n'amabara kugeza ibice bigoye nk'amaso cyangwa ibiziga
  5. Which named CNN is associated with the influential 2012 ImageNet classification result?
    • AlexNet
    • ResNet
    • Vision Transformer
    • SqueezeNet
  6. Ni ubuhe buryo bwo kubara bubaho mugihe akayunguruzo gakoreshwa mubice by'ishusho?
    • Pigiseli zitondekanye kuva mwijimye kugeza kumurika
    • Ipamba ryasibwe kurishusho
    • Buri buremere bugwizwa na pigiseli yuzuye, kandi ibicuruzwa byegeranijwe
    • Pigiseli ihindurwa inyuguti
  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