Ikibazo gihuza ibibazo · Biragoye Urwego

Ikibazo cya Capsule

Kugenzura capsule vectors, igice-kuri-inzira zose, gushiraho amakuru, amanota yamasezerano n'impamvu inzira yogukora ishobora kubahenze.

Inzira zijyanye no kuyoboraImiyoboro ya Capsule
Ikibazo 1 Bya 8

Mumuyoboro wa capsule, UBURENGANZIRA bwibisohoka bya capsule byerekana iki?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Mumuyoboro wa capsule, UBURENGANZIRA bwibisohoka bya capsule byerekana iki?
    • Birashoboka ko urwego ruhari
    • Ibara ryibintu byagaragaye
    • Igipimo cyo kwiga kuri kiriya cyiciro
    • Umubare wa neuron muri capsule
  2. Ni ikihe kibazo kijyanye na CNN isanzwe yari imiyoboro ya capsule yagenewe gukemura?
    • Buhoro buhoro imyitozo kuri GPU
    • Gutakaza umubano utandukanye / igice-cyose, kwemera ibice byo mumaso byijimye
    • Kudashobora gutunganya amashusho yamabara
    • Ibipimo bike cyane byo kwiga
  3. Ni irihe zina rya algorithm ihitamo capsules yo murwego rwo hasi ihuza na capsules yo murwego rwohejuru?
    • Gusubira inyuma mugihe
    • Gukata buhoro buhoro
    • Imikorere ihindagurika-by-amasezerano
    • Ibisanzwe
  4. Ninde watangije umuyoboro wa capsule hamwe na dinamike igenda muri 2017?
    • Yann LeCun na bagenzi be
    • Ian Goodfellow na bagenzi bawe
    • Vaswani na bagenzi be
    • Sabour, Frosst, na Hinton
  5. Niyihe ntego yimikorere ya 'squash' mumurongo wa capsule?
    • Kugirango usanzwe uburebure bwa vector kugeza hagati ya 0 na 1 mugihe ukomeza icyerekezo
    • Gusiba capsules idakoreshwa
    • Guhindura amashusho kuri graycale
    • Kongera ubujyakuzimu bwikora
  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