What is it about?
Self-learning software is able to improve its behaviour at runtime by using modern AI algorithms. Self-learning software can respond to unforeseen environmental situations or changing requirements. However, whether the software will learn the right things depends on the quality of the data based on which the system learns. We present how to consider the quality of data when building self-learning software.
Featured Image
Photo by Jackson Sophat on Unsplash
Why is it important?
Considering the data quality for self-learning systems is important, as otherwise the system may take very long to learn, may not be able to respond to unforeseen changes, or plainly learn wrong things.
Perspectives
This keynote summary shed light on important issues to consider and also provides an outlook on future possible research in this area.
Andreas Metzger
Universitat Duisburg-Essen
Read the Original
This page is a summary of: Data quality issues in online reinforcement learning for self-adaptive systems (keynote), November 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3549037.3570194.
You can read the full text:
Contributors
The following have contributed to this page
