HejuruUbuyobozi bukurikira
Ibipimo bya AI Uburinganire: Uburinganire bwa Demokarasi Kuringaniza
Tekiniki
UMUYOBOZI W'umuryango
Kuringaniza kutabogamye nigipimo cyerekana impamvu zuburinganire: kubintu bimwe kugiti cye hamwe nibihe byabayeho, guhanura bigomba kuguma kumera kwisi yerekana icyitegererezo aho isi irinzwe itandukanye.
Umva iki gitaboAI-byavuzwe · ~3 min
Ibipimo birashobora kwerekana inzira zitaziguye itsinda ryoroheje-parite igenzura ryabuze, ariko biterwa nurugero rwimpamvu nimpamvu zaciwe ninzira zigomba kubarwa nkizemewe.
Kusner, Loftus, Russell and Silva introduced counterfactual fairness in a 2017 NeurIPS paper using structural causal models. Informally, a predictor is counterfactually fair for an individual if its prediction in the observed world is the same as its prediction in a counterfactual world in which that individual belonged to a different protected group, given the same background circumstances. The method asks more than whether two groups have equal average outcomes: it asks whether changing the protected attribute in a causal model would change the particular person’s prediction. A structural causal model represents variables and the causal relationships used to generate them. The analyst intervenes on the protected attribute and evaluates the prediction in the resulting counterfactual world. The paper demonstrates the idea in a law-school success prediction example. This does not establish that counterfactual fairness is the uniquely correct ethical or legal standard; it formalizes one fairness intuition under specified causal assumptions. The assumptions carry normative weight. The analyst must decide which variables are causes, which observed features are descendants of protected status, which causal pathways are impermissible, and what “same person in a different group” means. In practice, the relevant counterfactual may be unobservable and the causal graph may be uncertain. Measurement error, hidden confounding and historical discrimination can undermine estimates. A system can satisfy a chosen counterfactual criterion while still producing group-level disparities or harmful outcomes under another fairness definition. Conversely, a predictor can use a protected attribute in a model to correct a harmful proxy path, depending on the causal policy chosen. Reports should publish the model, assumptions, permitted and prohibited pathways, uncertainty and comparisons to other measures rather than presenting one score as proof of fairness.
Inguzanyo yerekana niba icyemezo cyinguzanyo cyahinduka mugihe ubwoko bwabasabye butandukanye mugihe igitekerezo cyimpamvu cyicyitegererezo cyagize izindi mpamvu zifatika zikosorwa.
Itsinda ritanga akazi ripima niba amanota ahinduka munsi yuburinganire aho gushingira gusa kubiciro byatoranijwe muri rusange.
Umushakashatsi inyandiko zikomoka kumuranga urinzwe zifatwa nkibintu byemewe mbere yo kubara ibyahanuwe.
Umugenzuzi agereranya ibisubizo bivuguruzanya ningaruka zinyuranye, kalibrasi hamwe ningero-yikigereranyo kuko ntagipimo kimwe gisobanura neza ubutabera.
Ubushakashatsi bukomeje guteza imbere uburyo buboneye nuburyo bwibishushanyo mbonera. Amakipe agomba gufata imyanzuro idahwitse nkibisabwa kubitekerezo byicyitegererezo, kugumana isesengura ryibyiyumvo, no kubikoresha nibindi bisobanuro bya tekiniki namategeko aho kuba nkigipimo kimwe rusange. Bika itariki yanditseho isoko yibanze cyangwa wige inyuma ya buri kirego hanyuma usubiremo imyanzuro mugihe hagaragaye ibimenyetso bishya cyangwa ibisobanuro birambuye. Ibibazo byafunguye birimo uburyo bwo kwemeza inzira zitera mugihe inyandiko zuzuye kandi abaturage ntibavuga rumwe kubyerekeye inzira zemewe.
Ibaruwa y'amakuru y'ubuntu
Inkuru eshatu zizewe za AI buri gitondo cy'iminsi y'akazi, zanditse mu rurimi rworoshye. Ubuntu iteka ryose, nta kwamamaza.
Imeri imwe buri munsi y'akazi. Kwiyimura mu buryo bumwe. Ntitwigera tugurisha cyangwa ngo dusangire aderesi yawe.
Isuzume
Ibisubizo ako kanya kuri buri kibazo, n'icyemezo gishobora gusangirwa gifite ID yagenzurwa umaze gutsinda isomo.
Fasha uburezi bwa AI bw'ubuntu. AI Understanding ni umuryango utegamiye kuri leta wa 501(c)(3) — nta kwamamaza, nta kwishyura, iteka ryose. Tanga impano
Kuringaniza kutabogamye nigipimo cyerekana impamvu zuburinganire: kubintu bimwe kugiti cye hamwe nibihe byabayeho, guhanura bigomba kuguma kumera kwisi yerekana icyitegererezo aho isi irinzwe itandukanye. Ibipimo birashobora kwerekana inzira zitaziguye itsinda ryoroheje-parite igenzura ryabuze, ariko biterwa nurugero rwimpamvu nimpamvu zaciwe ninzira zigomba kubarwa nkizemewe.
Ibipimo bigereranya ibyo umuntu yahanuye hamwe nubuhanuzi buvuguruzanya munsi yagaciro karinzwe-ikiranga agaciro.
Urupapuro rutezimbere ibipimo ukoresheje ibikoresho biva mubitekerezo, harimo imiterere yimpamvu.
Muburyo bwimiterere yimpamvu, uwasesenguye ashyiraho ikiranga kirinzwe kurindi gaciro kandi agasuzuma ibyo umuntu umwe yahanuye mwisi itandukanye.
Ibipimo byihariye kandi bitera impamvu, aho kugereranya gusa ibipimo rusange.
Uburyo buterwa nuburyo bwimiterere yimpamvu nisesengura ibyemezo byerekeranye nimpamvu.
Komeza wige
Abandi bayobozi batoranijwe kuriyi ngingo
HejuruUbuyobozi bukurikira
Ibipimo bya AI Uburinganire: Uburinganire bwa Demokarasi Kuringaniza
Tekiniki