The challenge of crafting intelligible intelligence

2019/05/21 by Daniel S. Weld, Gagan Bansal · 13 citations
Decision Sciences · Computer Science · #Scientific Computing and Data Management #Semantic Web and Ontologies #Data Quality and Management

paper · pdf · doi:10.1145/3282486

Abstract

To trust the behavior of complex AI algorithms, especially in mission-critical settings, they must be made intelligible.

Citations

• XPLAIN: a system for creating and explaining expert consulting programs

Cited by

• People Can Accurately Predict Behavior of Complex Algorithms That Are Available, Compact, and Aligned
• Seven HCI Grand Challenges
• Towards Transparent Ethical AI: A Roadmap for Trustworthy Robotic Systems
• AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration
• Neuroprediction and A.I. in Forensic Psychiatry and Criminal Justice: A Neurolaw Perspective. [europepmc]
• Principles and Practice of Explainable Machine Learning. [europepmc]
• Eight human factors and ergonomics principles for healthcare artificial intelligence. [europepmc]
• Understanding Is a Process. [europepmc]
• Quality Models for Artificial Intelligence Systems: Characteristic-Based Approach, Development and Application. [europepmc]
• Achieving descriptive accuracy in explanations via argumentation: The case of probabilistic classifiers. [europepmc]
• GradeAid : a framework for automatic short answers grading in educational contexts-design, implementation and evaluation. [europepmc]
• Can Generative AI and ChatGPT Break Human Supremacy in Mathematics and Reshape Competence in Cognitive-Demanding Problem-Solving Tasks? [europepmc]
• Why we do need explainable AI for healthcare. [europepmc]

Related

• The Challenge of Crafting Intelligible Intelligence
• Building Safer AGI by introducing Artificial Stupidity
• Next Wave Artificial Intelligence: Robust, Explainable, Adaptable, Ethical, and Accountable
• Unexplainability and Incomprehensibility of Artificial Intelligence
• Knowledge-intensive Language Understanding for Explainable AI