Towards Identifying and Managing Sources of Uncertainty in AI and Machine Learning Models - An Overview
arXiv:1811.11669v111 citations
Originality Synthesis-oriented
AI Analysis
This is an incremental overview paper addressing uncertainty management for practitioners and researchers in AI and ML.
The paper tackles the problem of quantifying and managing uncertainties in AI and machine learning models, providing an overview of state-of-the-art methods for identifying and analyzing these uncertainties.
Quantifying and managing uncertainties that occur when data-driven models such as those provided by AI and machine learning methods are applied is crucial. This whitepaper provides a brief motivation and first overview of the state of the art in identifying and quantifying sources of uncertainty for data-driven components as well as means for analyzing their impact.