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

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...

Full description

Bibliographic Details
Main Authors: Navdeep Gill, Patrick Hall, Kim Montgomery, Nicholas Schmidt
Format: Article
Language:English
Published: MDPI AG 2020-02-01
Series:Information
Subjects:
deep learning
disparate impact
explanation
fairness
gradient boosting machine
interpretable
machine learning
neural network
python
Online Access:https://www.mdpi.com/2078-2489/11/3/137

Internet

https://www.mdpi.com/2078-2489/11/3/137

Similar Items