Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo Cyinshi cyo Kwiga

Gereranya mubyerekanwe hamwe na metric-ishingiye kuri bike-wize, hamwe ninshingano / kubaza inshingano, kubara prototype, kumenyesha, no gutumiza vuba.

Inzira zijyanye no kuyoboraKwiga Kurasa Bake
Ikibazo 1 Bya 8

In an N-way K-shot classification episode, what does K count?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. In an N-way K-shot classification episode, what does K count?
    • The number of classes
    • Labeled support examples per class
    • All parameters in the model
    • The number of optimization epochs
  2. Iyo ururimi runini rwicyitegererezo rukora-murwego rwo kwiga-kurasa byihuse, bigenda bite kuburemere bwarwo?
    • Bahinduwe neza gato kurugero rwihuse
    • Basubijwe kumurongo wihariye
    • Ntibahinduka; ingero ziteganya gusa guhanura
    • Bagereranijwe hamwe nurugero rwo gushiramo
  3. Ni irihe tandukaniro nyamukuru riri hagati ya zeru-kurasa na bike-kurasa?
    • Zeru-shoti nta ngero zakozwe; amasasu make atanga bike
    • Zeru-shoti ikoresha moderi ntoya kuruta kurasa
    • Zeru-shoti ikora neza kuruta kurasa
    • Zeru-shoti isaba amakuru yimyitozo yanditseho mugihe amafuti make atabikora
  4. How can prior learning contribute to a few-shot task?
    • It guarantees every arbitrary demonstration yields the intended rule
    • It requires copying each example as every final answer
    • It necessarily retrains all network weights during prompting
    • It can supply useful learned patterns or representations for interpreting the small support set
  5. Ninde usobanura metric-ishingiye kuburyo buke-burasa nkumuyoboro wa prototypical?
    • Yandika urugero ibirango mububiko bwo gushakisha
    • Itanga ingero zubukorikori kugeza zifite ibihumbi
    • Iragereranya icyitegererezo gishya nikigereranyo cyo gushyiramo ingero nke za buri cyiciro kandi kigatora hafi
    • Ikoresha imbaraga zo kwigira kubitekerezo byabantu
  6. Abimenyereza basanga guhindura gusa ingero mumasasu make ahita ahindura ukuri. Ibi byerekana iki?
    • Ikosa ryibikoresho muri GPU
    • Iyo mikorere mike-irashobora kuba yunvikana kurugero no gutondeka
    • Ko icyitegererezo gikwiranye nikizamini
    • Iyo zeru-zeru ntibyashoboka
  7. A class has embedded support points (0,0) and (2,0). What arithmetic-mean prototype does the stated prototypical method form?
    • (2,0)
    • (0,2)
    • (2,2)
    • (1,0)
  8. Which distinction defines support and query roles in the original prototypical-network episode?
    • Support labels construct class prototypes; separate query items evaluate classification
    • Query labels must be copied into every support prototype
    • Support items contain no labels by definition
    • The two sets must always contain exactly the same sampled examples