Ikibazo gihuza ibibazo · Hagati Urwego

Ibisubizo Byibisubizo muri ML Sisitemu Ikibazo

Kurikirana uburyo ibikorwa byintangarugero bigira ingaruka kubisubizo byagaragaye hamwe namakuru yamahugurwa azaza, hanyuma umenye uburyo bwo guhitamo no kubogama.

Ikibazo 1 Bya 8

Nigute uwatanze inama ashobora gukora ibitekerezo?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Nigute uwatanze inama ashobora gukora ibitekerezo?
    • Guhitamo kwayo bigira ingaruka gukanda nyuma bigahinduka ibimenyetso byamahugurwa
    • Ubuhanuzi bwabwo ntibwigeze bubikwa
    • Ibipimo by'icyitegererezo birashizweho
    • Abakoresha ntibashobora gusubiza ibyifuzo
  2. Ni ukubera iki ibisubizo byo gutanga akazi bishobora kubura kubasaba kugenzurwa nicyitegererezo?
    • Ibirango byabo buri gihe ni bibi
    • Ntabwo bakira amahirwe yo hasi atanga umusaruro
    • Icyitegererezo kibika ibisubizo byose byikora
    • Ikiranga igishushanyo gikuraho ibirango
  3. Kwandika ibintu byerekanwe bifasha gutandukanya iki?
    • Kunanirwa kwa GPU kuva igihe cya API
    • Amahugurwa yamakuru ahereye kubipimo by'icyitegererezo
    • Amahirwe yo kwerekana uhereye kubakoresha ibimenyetso
    • A label from a feature name
  4. Ni ryari isuzuma rinyuranye rishobora kwizerwa?
    • When the target policy matches the logging policy
    • When all propensities are recorded correctly
    • When randomized experiments have enough data
    • When the new policy chooses actions with no support in logged data
  5. Kuki ukurikirana ibirango bikurikirana amanota cyangwa itsinda?
    • Coverage proves the model is fair
    • Observation rates may differ because the model routes cases differently
    • Scores are always outcomes
    • Every group must have identical labels
  6. Which data-collection strategy can reveal outcomes for less-shown alternatives?
    • Remove the need for logging
    • Guarantee every recommendation is relevant
    • Gather evidence about alternatives that a deterministic policy rarely shows
    • Make all users receive identical items
  7. Why might more training data fail to remove feedback-loop bias?
    • Bias is always random
    • Larger datasets cannot contain labels
    • Training never uses user interactions
    • New data may be generated by the same selective policy
  8. What kind of system property is a feedback loop?
    • A property of the deployed sociotechnical process and its data collection
    • Only a gradient calculation
    • A model architecture name
    • A feature scaling method