Interpretable causal systems: interpretability and causality in machine learning for human and nonhuman decision-making

<p>In order to integrate machine learning into human decision-making in a useful way, we must trust machine learning systems enough in our reasoning processes. To evaluate a system’s trustworthiness, humans naturally seek interpretable causal systems to understand outcomes, make decisions, and...

Popoln opis

Bibliografske podrobnosti
Glavni avtor: Graham, L
Drugi avtorji: Osborne, M
Format: Thesis
Jezik:English
Izdano: 2020
Teme: