Machine Learning Techniques for Accountability

Authors

  • Been Kim Google Brain
  • Finale Doshi-Velez Harvard University

Abstract

Artificial intelligence systems have provided us with many everyday conveniences. We can easily search for information across millions of webpages via text and voice. Paperwork processing is increasingly automated. Artificial intelligence systems flag potentially fraudulent credit-card transactions and filter our e-mail. Yet these artificial intelligence systems have also experienced significant failings. Across a range of applications, including loan approvals, disease severity scores, hiring algorithms, and face recognition, artificial-intelligence–based scoring systems have exhibited gender and racial bias. Self-driving cars have had serious accidents. As these systems become more prevalent, it is increasingly important that we identify the best ways to keep them accountable.

Published

2021-04-12

How to Cite

Kim, B. ., & Doshi-Velez, F. (2021). Machine Learning Techniques for Accountability. AI Magazine, 42(1), 47-52. Retrieved from https://ojs.aaai.org/index.php/aimagazine/article/view/7481

Issue

Section

Special Topic Articles