Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Hooska Jinsiga iyo Aqoonsiga Wejiga eexashada Kediska Hantidhawrka

Wuxuu tijaabiyaa habka xisaabinta is-goysyada ee hadhka jinsiga, faraqa u dhexeeya kala soocida jinsiga iyo aqoonsiga, iyo natiijooyinka tirakoobka NIST.

Wadooyinka haga ee la xidhiidhaHadhka Jinsiga Wejiga Aqoonsiga Eexda
Su'aal 1 ee 8

Adeegyada falanqaynta wajiga ee shirkaddee ayay daraasadda asalka ah ee Gender Shades baartay?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Adeegyada falanqaynta wajiga ee shirkaddee ayay daraasadda asalka ah ee Gender Shades baartay?
    • Google, Apple and Meta
    • Amazon, Kairos and Clearview
    • IBM, Microsoft and Face++
    • NEC, Idemia and Cognitec
  2. Maxay ka koobnayd Pilot Parliaments Benchmark?
    • Images of members of parliament from three African and three European countries
    • Celebrity photos scraped from the web
    • Mugshots from US police departments
    • Synthetic faces generated by a neural network
  3. Miisaankee ayay cilmi-baarayaashu u isticmaaleen inay ku calaamadeeyaan nooca maqaarka?
    • The Monk Skin Tone scale
    • The Fitzpatrick scale
    • The Munsell color system
    • A self-reported race category
  4. Waa maxay hawsha ay Gender Shades dhab ahaan cabbiraysay?
    • One-to-many face identification against police databases
    • Emotion recognition
    • Face detection in video
    • Gender classification
  5. Waa kee koox-hoosaadkii lahaa heerarka qalad ee ugu sarreeya ee Gender Shades?
    • Haweenka maqaarka madow
    • Lighter-skinned women
    • Darker-skinned men
    • Ragga maqaarka iftiinka leh
  6. What did the 2019 "Actionable Auditing" follow-up find?
    • No vendor had changed its system
    • All disparities had been eliminated industry-wide
    • Audited companies had narrowed their gaps, while unaudited vendors showed similar disparities
    • The original study's data had been fabricated
  7. Why can a single similarity threshold produce unequal outcomes across groups?
    • Thresholds only apply to men
    • The same threshold can yield very different false match rates for different groups
    • Thresholds are chosen at random for each query
    • Thresholds affect speed but not errors
  8. Which vendor response happened in June 2020?
    • Microsoft began selling facial recognition to all US police
    • Face++ published its training data
    • NIST banned facial recognition
    • IBM said it would leave the general-purpose facial recognition business