November 2026
368 pages
13h 30m
English
Artificial intelligence (AI) increasingly acts as a decision-maker in high-stakes domains such as healthcare, finance, education, and justice. While AI offers efficiency and consistency, it also risks amplifying bias when models treat some groups more favorably than others. Ensuring fairness is therefore central to building trustworthy AI.
provide systematic ways to measure bias. They quantify whether outcomes are balanced across demographic groups, whether errors are distributed equally, and whether sensitive attributes such as race or gender unduly influence predictions. This appendix introduces fairness metrics in a uniform structure: ...
Read now
Unlock full access