Guide-yakabatana mibvunzo · Pakati Nhanho

Federated Learning Quiz

Nyorera mafederated modhi magadzirirwo, huremu hweavhareji, uye kuchengetedzwa kuunganidzwa, kusanganisira nei kuchengeta marekodhi emunharaunda haisi vimbiso yakakwana yekuvanzika.

Nzira dzekutungamira dzinoenderanaFederated Learning
Mubvunzo 1 ye 8

How does federated learning train a shared model without centralizing user data?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. How does federated learning train a shared model without centralizing user data?
    • Dzidzisa imwe modhi nekuisa data remunhu wese kune yepakati server
    • Shandisa chete synthetic data uye usambofa data chaiyo
    • Dzidzisa muenzaniso wakagovaniswa nekutumira zvigadziriso zvemodhi panzvimbo yedata yakabikwa kune server
    • Mhanya yakaparadzana, isina hukama modhi pane yega yega mudziyo zvachose
  2. Chii chinoitwa neFederated Averaging (FedAvg) algorithm pane server?
    • Inodzima mhando dzese dzevatengi
    • Avhareji yehuremu yekuvandudza kubva kune vatengi, kazhinji inoyerwa nehuwandu hwe data
    • Inotumira mbishi data kumashure kune vatengi
    • Inodzidzisa modhi yacho pachayo
  3. Ndechipi chigadzirwa chine mukurumbira chakashandisa kudzidza kwakabatana kuvandudza fungidziro?
    • Yepakati spam email sefa
    • Satellite yemamiriro ekunze
    • Mutambo wevhidhiyo console
    • Google's Gboard keyboard
  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. Sei zvigadziriso zvemodhi zvisiri zvoga zvisiri zvega zvakazara?
    • Zvigadziriso zvinogara zvisina ruzha ruzha
    • Zvigadziriso zvinogona kuburitsa ruzivo nezve iri pasi pe data
    • Zvigadziriso zvine data raw isina kuchinjwa
    • Zvigadziriso hazvigone kutumirwa nepanetiweki
  6. Nderipi dambudziko rinokonzeresa 'risiri-IID' data mukudzidza kwakabatana?
    • Zvese zvishandiso zvine data rakafanana, saka hapana chinodzidzwa
    • Sevha inopera mundangariro ipapo ipapo
    • Iyo modhi inogona chete kudzidza mifananidzo
    • Kugovewa kwedata kwevatori vechikamu kunosiyana zvakanyanya, zvichiita kuti avhareji iome
  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