quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz jàng federaal

Jëfandikool yeesali model federaal, moyenne pondérée, ak agrégation bu wóor, boole ci lu tax dencu dokimaa yu bees yi nekkul garanti privacy bu mat sëkk.

Yooni njiit yu jëm ciJàng bu boole
Laaj 1 de 8

Naka lay def ba jàng federaal di tàggat xeetu jëfandikukat buñ bokk te du boole ay done jëfandikukat?

Xoolaatal laaj bu nekk8 laaj

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

  1. Naka lay def ba jàng federaal di tàggat xeetu jëfandikukat buñ bokk te du boole ay done jëfandikukat?
    • Taggat benn model ci yebbi done yu bees yu ku nekk ci benn serwër bu mag
    • Jëfandikool ay done yuñ defar rek te doo jëfandikoo ay done yu dëggu
    • Taggat benn model buñ bokk di yónnee ay yeesali model ci plaasu done yu bees yi ci serwër bi
    • Doxal benn model bu wuute, bu amul benn lëkkaloo ci aparey bu nekk ba fàww
  2. Lan la algorithm moyenne fedérée (FedAvg) di def ci serwër bi?
    • efaase bépp model kiliyaan
    • Moyenne coppite yu poid yi bawoo ci kiliyaan yi, ñu koy faral di pondéree ci bariwaayu done yi
    • Yonneewaat done yu bees yi kiliyaan yi
    • Dafay tàggat model bi ci boppam
  3. Ban produit moo gëna jëfandikoo njàngum federaal ngir gëna mëna wax luy am?
    • Seggal imeel spam bu mag
    • Satelit meteo
    • Benn konsol jeu video
    • Google
  4. Why might a hospital collaboration investigate federated training?
    • It can train through local computations without centrally pooling patient records
    • It automatically makes all sharing legally compliant
    • It removes every risk of revealing patient information
    • It requires no evaluation of the resulting model
  5. Lan moo waral yeesali model yi kese duñu nekk lu nëbbu ci saasi?
    • Coppite yi dañuy nuru bruit yu bari
    • Coppite yi mën nañu ba leegi sacc ay leeral ci done yi ci suuf
    • yeesal yi deñuy denc done yu bees yi
    • Mënu yónnee yeesali reso yi
  6. Ban jafe-jafe la done yu 'amul IID' mëna jur ci njàng mu boole?
    • Bépp aparey amna done yu nuróo, kon dara duñu jàng
    • Serveur bi dafay jeexal mémoire bi ci saasi
    • Modèle bi mënul jàng ludul nataal
    • Done yiñ séddale ci ñi ci bokk wuute nañu lool, moo tax moyenne bi gëna jafe
  7. Two FedAvg clients return scalar weights 0 and 10 after using 1 and 3 training examples. What is the data-weighted average?
    • 7.5
    • 5
    • 10
    • 2.5
  8. What does a successful secure-aggregation protocol aim to reveal to the federated server?
    • Every client’s raw training record
    • Only a participant’s device password
    • The aggregate update rather than each participant’s individual value
    • A complete guarantee against all information in the aggregate