Interpretability and Decision-Making
Patrick and Andrew discuss the challenges of interpretability in AI algorithms and the impact it has on decision-making. They highlight incidents where the algorithm's authority is unquestionable, leading to potential problems and lack of appeal for those affected. They emphasize the importance of understanding the human and process factors involved in AI incidents.In this clip
From this podcast
Practical AI
When AI goes wrong
Related Questions
What is the challenge around explainability in AI?
What is the challenge around explainability in AI as discussed in the episode When AI goes wrong and the clip Interpretability and Decision-Making?
What is the challenge around explainability in AI as discussed in the episode Evaluating Model Explainability Methods with Sara Hooker - TWiML Talk #189 and the clip Interpretability in AI?