quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz jàng bu néew

Teg ci misaal yi ci biir kontekst bi ak jàngat bu lalu ci metrik yu néew, ak cër yi ñuy jàppale/laajte, xayma prototype, notaasioŋ, ak komànd bu gaaw.

Yooni njiit yu jëm ciFew Shot di jàng
Laaj 1 de 8

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

Xoolaatal laaj bu nekk8 laaj

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

  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. Su benn modelu làkk bu yaatu defee ay njàngale yu néew ci biir contexte ci benn prompt, lan mooy dall ci diisaayam?
    • Dañu leen raññe tuuti ci misaal yu gaaw yi
    • Dañu leen di reset ci benn poñ de saytu buñ jagleel benn liggéey
    • Duñu soppeeku; misaal yi dañuy tënk li ñuy wax rek
    • Dañu leen di méngale ak misaalu embeddings yi
  3. Lan mooy wuutale zero-shot ak few-shot?
    • Zero-shot joxeewul misaal yuñ liggéey; few-shot dafay joxe yenn
    • Zero-shot dafay jëfandikoo model bu gëna ndaw
    • Zero-shot mooy gëna baax ci few-shot
    • Zero-shot defay laaj ay done yuñ etikete ci taggat waaye few-shot soxlawul
  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. Lan mooy leeral ab pexem metrik bu sukkandiko ci ay nataal yu néew yu melni ab reso prototypique?
    • Dafay bind misaali etiket ci base de done ngir seetlu
    • Dafay defar misaal yuñ defar ba keroog muy am ay junni
    • Dafay méngale misaal bu bees ak misaal yu néew yi ci klaas bu nekk, ba noppi tànn bi gëna jege
    • Dafay jëfandikoo njàng mu am doole ci feedback nit
  6. Praktisien bi dafa gis ni su amee misaal yu bees yu ñuy raññewaat ci diir bu gàtt, loolu dafay soppi njubte gi. Lu loolu di wone ?
    • Ab bug hardware ci GPU bi
    • Boobu performance bu néew mën na nekk lu am solo ci misaalu njuréef ak formatage
    • Ni model bi defa méngoo bu baax ak test bi
    • Boobu zero-shot du mëna am
  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