Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Revealing Neural Network Bias to Non-Experts Through Interactive Counterfactual Examples
8
Zitationen
6
Autoren
2020
Jahr
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.
Ähnliche Arbeiten
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
2017 · 20.408 Zit.
Generative Adversarial Nets
2023 · 19.841 Zit.
Visualizing and Understanding Convolutional Networks
2014 · 15.253 Zit.
"Why Should I Trust You?"
2016 · 14.286 Zit.
On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)
2024 · 13.132 Zit.