Guide-yakabatana mibvunzo · Zvakaoma Nhanho

Capsule Networks Quiz

Inotarisa capsule vectors, chikamu-kusvika-yakazara routing, posa ruzivo, zvibvumirano zvibodzwa uye nei iterative routing inogona kudhura.

Nzira dzekutungamira dzinoenderanaCapsule Networks
Mubvunzo 1 ye 8

Munetiweki yecapsule, UREFU hwekapule's output vector inomirirei?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Munetiweki yecapsule, UREFU hwekapule's output vector inomirirei?
    • Mukana wekuti sangano riripo
    • Ruvara rwechinhu chakaonekwa
    • Chiyero chekudzidza cheiyo layer
    • Huwandu hwema neurons mu capsule
  2. Ndeipi dambudziko neyakajairwa CNNs yaive capsule network yakanyatso gadzirirwa kugadzirisa?
    • Kunonoka kudzidziswa paGPUs
    • Kurasikirwa kwepakati/chikamu-chese hukama, semuenzaniso. kubvuma majumbled face parts
    • Kusagona kugadzirisa mifananidzo yemavara
    • Maparamita mashoma ekudzidza
  3. Iri zita regorgorithm iro rinosarudza kuti ndeapi ezasi-level capsules anobatana neapi epamusoro-level capsules?
    • Backpropagation kuburikidza nenguva
    • Gradient clipping
    • Dynamic routing-ne-chibvumirano
    • Batch normalization
  4. Ndiani akaunza iyo capsule network ine dynamic routing muna 2017?
    • Yann LeCun nevamwe vaaishanda navo
    • Ian Goodfellow nevamwe vaaishanda navo
    • Vaswani nevamwe vaaishanda navo
    • Sabour, Frosst, uye Hinton
  5. Chii chinangwa chebasa re'squash' mucapsule network?
    • Kujairisa kureba kwevekita kusvika pakati pe0 ne1 uchichengeta gwara rayo
    • Kudzima capsules dzisina kushandiswa
    • Kushandura mifananidzo kuita grayscale
    • Kuwedzera kudzika kwetiweki otomatiki
  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