Revealing Neural Network Bias to Non-Experts Through Interactive Counterfactual Examples

2020/01/07 by Myers, Chelsea M., Freed, Evan, Pardo, Luis Fernando Laris +3 · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC)

paper · doi:10.48550/arxiv.2001.02271

Abstract

AI algorithms are not immune to biases. Traditionally, non-experts have little control in uncovering potential social bias (e.g., gender bias) in the algorithms that may impact their lives. We present a preliminary design for an interactive visualization tool CEB to reveal biases in a commonly used AI method, Neural Networks (NN). CEB combines counterfactual examples and abstraction of an NN decision process to empower non-experts to detect bias. This paper presents the design of CEB and initial findings of an expert panel (n=6) with AI, HCI, and Social science experts.

Cited by

• On Explaining Proxy Discrimination and Unfairness in Individual Decisions Made by AI Systems

Related

• D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias
• BIASeD: Bringing Irrationality into Automated System Design
• Rolling in the deep of cognitive and AI biases
• Can AI Mitigate Human Perceptual Biases? A Pilot Study
• Designing Tools for Semi-Automated Detection of Machine Learning Biases: An Interview Study