СледваСледва в Отговорен потребител с изкуствен интелект
AI и поверителност
общество
РЪКОВОДСТВО за обществото
AI bias can arise from data, measurement, modeling choices, human judgments, and the wider system in which a model is used.
Чуйте това ръководствоAI-разказан · ~2 min
Some patterns can produce unfair or harmful outcomes. Evaluating bias requires defining the context and consequences, not merely removing a sensitive column from a dataset.
Examine how examples and labels were collected. Missing populations, inconsistent annotation, historical decisions, and selective measurement can shape what the model learns. A target label may reflect an old process rather than the underlying outcome people care about. Measure performance across relevant groups and conditions with suitable privacy controls. Report sample sizes and uncertainty. A small subgroup can have unreliable estimates, while a global average can hide a large and practically important disparity. Different fairness criteria answer different questions and can conflict. Equalizing one statistical measure does not settle every ethical or legal concern. Choose criteria with domain expertise and the participation of people affected by the system. Review the workflow around the model. How predictions are used, who can challenge an outcome, and how feedback is collected can change the distribution of harm. Evaluate mitigations for both their intended effect and possible new problems. Treat fairness as an ongoing assessment rather than a one-time certificate.
04Работен пример
In an invented test, group A has 900 examples with 95% accuracy, while group B has 100 examples with 60% accuracy.
The overall result is dominated by group A. Report group B separately and inspect its errors and sample uncertainty.
Investigate data coverage and workflow causes before choosing a mitigation.
Какво показва
These hypothetical counts illustrate why an aggregate score cannot establish equitable performance.
Compare error rates across realistic operating conditions with sample sizes shown.
Review whether a training label captures a past decision rather than the intended outcome.
Безплатен бюлетин
Три проверени AI истории всяка делнична сутрин, написани на достъпен език. Безплатно завинаги, без реклами.
Един имейл всеки делничен ден. Отписване с едно кликване. Никога не продаваме и не споделяме вашия имейл адрес.
Тествайте себе си
Незабавна обратна връзка за всеки отговор и сертификат за споделяне с подлежащ на проверка идентификационен номер, след като преминете курс.
Подкрепете безплатното AI образование. AI Understanding е 501(c)(3) с нестопанска цел — без реклами, без платен достъп, никога. Направете дарение
Not by that step alone. Proxy variables, labels, collection practices, and deployment decisions can still produce unequal outcomes.
Продължавай да учиш
Още ръководства, избрани за тази тема
СледваСледва в Отговорен потребител с изкуствен интелект
AI и поверителност
общество