Unexplainability and Incomprehensibility of Artificial Intelligence
arXiv:1907.03869
Abstract
Explainability and comprehensibility of AI are important requirements for intelligent systems deployed in real-world domains. Users want and frequently need to understand how decisions impacting them are made. Similarly it is important to understand how an intelligent system functions for safety and security reasons. In this paper, we describe two complementary impossibility results (Unexplainability and Incomprehensibility), essentially showing that advanced AIs would not be able to accurately explain some of their decisions and for the decisions they could explain people would not understand some of those explanations.
References in corpus (7)
- Towards A Rigorous Science of Interpretable Machine Learning
- Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures
- Hypercomputation: computing more than the Turing machine
- The Doctor Just Won't Accept That!
- Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions
- Personal Universes: A Solution to the Multi-Agent Value Alignment Problem
- Evaluating race and sex diversity in the world's largest companies using deep neural networks