Computer Science
A Review of Bias and Fairness in Artificial Intelligence
R. González-sendino, E. Serrano, et al.
Automating decision systems has revealed hidden biases in AI, challenging explainability and responsibility. This paper categorizes biases across AI development phases, revises fairness metrics for auditing data and agnostic models, and proposes a novel taxonomy of bias-mitigation procedures spanning pre-processing, training, post-processing, and transversal actions. This research was conducted by Rubén González-Sendino, Emilio Serrano, Javier Bajo, and Paulo Novais.
Related Publications
Explore these studies to deepen your understanding of the subject.
