Artificial Intelligence in Automation

GAIA: Gaussian Processes for Automatic and Interpretable Anomaly Detection

01.12.2020 bis 01.12.2024

Gaussian Process Models are widely used in Bayesian Machine Learning as they can be applied when only limited data is available and can be directly interpreted. The GAIA project will employ such Gaussian Process Models in an extension to multivariate time series. The resultant model will therefore cover spatial as well as temporal information and should detect anomalies spanning both of these dimensions. On focus will be on how model selection influences the explainability of constructed models.

A latent variable model can be used, for example, to represent a process as is found in many industrial applications. Such processes are characterized through temporal data given as time series. In the project, a latent variable model should be learned in an unsupervised fashion as a Gaussian Process Model. Importantly, prior knowledge on the particular application domain can be exploited: While usually in Gaussian Processes the search for a fitting covariance function is expensive, domain knowledge can be introduced into the covariance matrix in the form of underlying differential equations which leads to hybrid and interpretable models.

Das Projekt wird gefördert durch:
Graduiertenkolleg Data-NInJA
Projektträger: Projektträger Jülich
Förderkennzeichen: 005-2010-0003
Förderlinien: Künstliche Intelligenz
Projektbeteiligte / Ansprechpartner: Prof. Dr. rer. nat. Markus Lange-Hegermann
Projektmitarbeitende: Andreas Besginow, M. Sc.
Studienarbeit
Investigation into Model Selection for Gaussian Process Regression
Thomas Pawellek
19.10.2021 bis 14.12.2021
Bachelorarbeit
Approximate Model Selection Criteria for Gaussian Process Regression
Thomas Pawellek
19.01.2022 bis 16.03.2022
Gefördert durch
Projektträger