A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing

This manuscript outlines a viable approach for training and evaluating machine learning systems for high-stakes, human-centered, or regulated applications using common Python programming tools. The accuracy and intrinsic interpretability of two types of constrained models, monotonic gradient boostin...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Navdeep Gill, Patrick Hall, Kim Montgomery, Nicholas Schmidt
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	MDPI AG 2020-02-01
סדרה:	Information
נושאים:	deep learning disparate impact explanation fairness gradient boosting machine interpretable machine learning neural network python
גישה מקוונת:	https://www.mdpi.com/2078-2489/11/3/137
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!