How to certify machine learning based safety-critical systems? A systematic literature review
Abstract Context Machine Learning (ML) has been at the heart of many innovations over the
past years. However, including it in so-called “safety-critical” systems such as automotive or …
past years. However, including it in so-called “safety-critical” systems such as automotive or …
Machine learning with a reject option: A survey
Abstract Machine learning models always make a prediction, even when it is likely to be
inaccurate. This behavior should be avoided in many decision support applications, where …
inaccurate. This behavior should be avoided in many decision support applications, where …
[HTML][HTML] Statistical mechanics of on-line learning under concept drift
We introduce a modeling framework for the investigation of on-line machine learning
processes in non-stationary environments. We exemplify the approach in terms of two …
processes in non-stationary environments. We exemplify the approach in terms of two …
Toward airworthiness certification for artificial intelligence (AI) in aerospace systems
A Henderson, S Harbour… - 2022 IEEE/AIAA 41st …, 2022 - ieeexplore.ieee.org
Boeing “produced an airplane that had an unsafe condition” and admitted full responsibility
for the second of its 737 MAX plane crash in Ethiopia in October 2018, killing 189 people. A …
for the second of its 737 MAX plane crash in Ethiopia in October 2018, killing 189 people. A …
Fairness, accountability, sustainability, transparency (fast) of artificial intelligence in terms of hospitality industry
Artificial intelligence (AI) is playing very significant role in every domain of life and spreading
widely all across the globe. It covers all major fields like automation, hospitality industries …
widely all across the globe. It covers all major fields like automation, hospitality industries …
IDPS signature classification with a reject option and the incorporation of expert knowledge
H Kawaguchi, Y Nakatani… - 2022 21st IEEE …, 2022 - ieeexplore.ieee.org
As the importance of intrusion detection and prevention systems (IDPSs) increases, great
costs are being incurred to manually manage signatures, which are malicious …
costs are being incurred to manually manage signatures, which are malicious …
Concept drift adaptive physical event detection for social media streams
Event detection has long been the domain of physical sensors operating in a static dataset
assumption. The prevalence of social media and web access has led to the emergence of …
assumption. The prevalence of social media and web access has led to the emergence of …
Assed: A framework for identifying physical events through adaptive social sensor data filtering
Physical event detection has long been the domain of static event processors operating on
numeric sensor data. This works well for large scale strong-signal events such as …
numeric sensor data. This works well for large scale strong-signal events such as …
Interpretable locally adaptive nearest neighbors
When training automated systems, it has been shown to be beneficial to adapt the
representation of data by learning a problem-specific metric. This metric is global. We extend …
representation of data by learning a problem-specific metric. This metric is global. We extend …
Precision and Recall Reject Curves
L Fischer, P Wollstadt - International Workshop on Self-Organizing Maps …, 2024 - Springer
For some classification scenarios, it is desirable to use only those classification instances a
trained model associates with a high certainty. To evaluate such high-certainty instances …
trained model associates with a high certainty. To evaluate such high-certainty instances …