Uncertainty Aware AI ML: Why and How
By Lance M. Kaplan, Federico Cerutti, Murat Sensoy, Alun David Preece, Paul Sullivan. 2018
22 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Alun David Preece
- Federico Cerutti
- Dave Braines
- Lance M. Kaplan
- Murat Sensoy
- Mani B. Srivastava
- Supriyo Chakraborty
- Angelika Kimmig
Citations in the corpus
- Rapid Trust Calibration through Interpretable and Uncertainty-Aware AI (2020, background): “It is particularly important to understand epistemic uncertainty in the coalition scenario.(37) At the start of an operation, coalition partners will deploy AI systems trained on historical data.”
- Uncertainty-aware situational understanding (2019, background): “(8) Given that in the absence of any evidence, the prior probability for pX is αX “ WaX, the evidence for opinion ωX is eX “ B”
- Explainable AI for Intelligence Augmentation in Multi-Domain Operations (2019, background): “…it is conceivable that, when enough data is available to classify the activity, the harmless dance could be identified by machine processing, in (Kaplan et al. 2018) we consider the case where recognising this activity requires local cultural knowledge and is handled by human-machine teaming:…”
- Stakeholders in Explainable AI (2018, background): “…a variety of methods being proposed to deal with them, including employing a portfolio of models to mitigate against weaknesses in individual models, and creating AI systems that build causal models of the world (Lake et al. 2017) and/or or are aware of their own uncertainty (Kaplan et al. 2018).”