Removing Spurious Features Can Hurt Accuracy and Affect Groups Disproportionately
Offered By: Association for Computing Machinery (ACM) via YouTube
Course Description
Overview
Explore a thought-provoking conference talk that delves into the unintended consequences of removing spurious features in machine learning models. Examine how this practice, often aimed at improving model performance, can paradoxically lead to decreased accuracy and disproportionately affect certain groups. Through a comprehensive analysis of various datasets and experimental setups, gain insights into the complex relationship between feature selection, model accuracy, and fairness in AI systems. Understand the implications of these findings for developing more robust and equitable machine learning algorithms, and consider the broader ethical considerations in AI research and development.
Syllabus
Introduction
Accuracy Drop
Setup
Data Sets
Results
Other Results
Conclusion
Taught by
ACM FAccT Conference
Related Courses
Social Network AnalysisUniversity of Michigan via Coursera Intro to Algorithms
Udacity Data Analysis
Johns Hopkins University via Coursera Computing for Data Analysis
Johns Hopkins University via Coursera Health in Numbers: Quantitative Methods in Clinical & Public Health Research
Harvard University via edX