Read the original document by opening this link in a new tab.
Table of Contents
1. INTRODUCTION
2. RELATED WORK
3. SOURCES OF BIAS
4. A BIASED WORLD
5. BIAS IN DATA GENERATION
Summary
This paper proposes a taxonomy of the various meanings of the term bias in conjunction with machine learning. It discusses different types of biases, their connections, and dependencies. The authors argue that terminology shapes problem identification and communication, especially in multidisciplinary work. The taxonomy is based on a survey of published research and aims to promote clear terminology and completeness in understanding bias in machine learning.