PofoliaShared via Pofolia

arXiv (Cornell University)· 2017· Preprint

A Unified Approach to Interpreting Model Predictions

Scott Lundberg, Su‐In Lee

Short summary

SHAP (SHapley Additive exPlanations) unifies six existing methods for interpreting complex AI model predictions, introducing a new class of additive feature importance measures with desirable theoretical properties.

AI-generated from the title and abstract; the full text is not read.

TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways, key points and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Field: Artificial Intelligence

Artificial IntelligenceComputer Science