Uncertainty Aware AI ML: Why and How
arXiv:1809.07882
Abstract
This paper argues the need for research to realize uncertainty-aware artificial intelligence and machine learning (AI\&ML) systems for decision support by describing a number of motivating scenarios. Furthermore, the paper defines uncertainty-awareness and lays out the challenges along with surveying some promising research directions. A theoretical demonstration illustrates how two emerging uncertainty-aware ML and AI technologies could be integrated and be of value for a route planning operation.
arXiv commentPresented at AAAI FSS-18: Artificial Intelligence in Government and Public Sector, Arlington, Virginia, USA
Cited by in corpus (5)
- Explainable AI for Intelligence Augmentation in Multi-Domain Operations
- Using Subjective Logic to Estimate Uncertainty in Multi-Armed Bandit Problems
- Fine-grained Uncertainty Modeling in Neural Networks
- The current state of automated negotiation theory: a literature review
- Learning a metacognition for object perception