quiz bu lëkkale ak tegtal · Dëgër Niveau

Laajte ci Reseau Capsule

Saytu vecteur capsule yi, yoon wi ci wàll wi yépp, leeral ci pose yi, poñ yiñ am ci déggoob bi ak lu tax yoon wi ñuy baamtu mën na seer.

Yooni njiit yu jëm ciReseau capsule
Laaj 1 de 8

Ci biir reso capsule, lan mooy LENGTH vecteur biy génne ci capsule bi?

Xoolaatal laaj bu nekk8 laaj

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

  1. Ci biir reso capsule, lan mooy LENGTH vecteur biy génne ci capsule bi?
    • Probabilite bi entite bi nekk
    • Kulòoru màndarga biñ gis
    • Tolluwaayu jàng bi ci layer boobu
    • limu neuron yi ci biir kapsul bi
  2. Ban jafe-jafe ak CNN yiñ miin lañu defar ngir saafara reso capsule yi?
    • Taggat bu yeex ci GPU yi
    • Ñàkk diggante barab/wàll-lépp, lu melni nangu cër yu jaxasoo ci kanam gi
    • Mënul jëfandikoo nataali melo
    • Parametre yu néew lañu wara jàng
  3. Luy turu algorithm biy wax ban kapsul bu gëna suufe mooy boole ak ban kapsul bu gëna kawe?
    • Backpropagation ci diir bi
    • Dagg degrade
    • Yoon dinaamik ci déggoob
    • Normalisasioŋ ci lots
  4. Kan moo dugal reso capsule bi am routage dynamique ci 2017?
    • Yann LeCun ak ay naataangoom
    • Ian Goodfellow ak ay naataangoom
    • Vaswani ak ay naataangoom
    • Sabour, Frost, ak Hinton
  5. Lan mooy njariñu fonction 'squash' ci reso capsule?
    • Normalise guddaayu vecteur bi diggante 0 ak 1 boole ci tëye yoon wi
    • Ngir efaase kapsul yiñ jëfandikoowul
    • Ngir soppi nataal yi ci grayscale
    • Ngir yokk xóotaayu reso bi ci saasi
  6. Which result did the original 2017 CapsNet paper report as evidence for routing-by-agreement?
    • Lower memory use than every CNN on ImageNet
    • Better recognition of highly overlapping digits than a convolutional net
    • No need for a training objective
    • Perfect performance on all affine transformations
  7. In the original capsule representation, what information is carried by the direction of a capsule’s output vector?
    • The probability that the entity is absent
    • The number of routing iterations
    • Instantiation or pose parameters of the represented entity
    • The loss assigned to the previous layer
  8. In routing-by-agreement, what makes a lower capsule’s prediction agree with a higher-level capsule?
    • Their capsule names begin with the same letter
    • Their vector lengths are exactly zero
    • They occur in the same image crop
    • Their predicted and output vectors have a large scalar product