jbueltemeier/scarce_data_gui: AI4ScaDa generalised Artificial Intelligence Workflow for Scarce Data

The innovation project AI4ScaDa of the it's OWL cluster of excellence is dedicated to the research and development of special AI techniques for profitable use in scenarios with little data, also known as Scarce Data. While the term Big Data describes a large amount of available and diverse data, Scarce Data refers to a limited amount or incomplete data sets, as they are often collected in laboratories or during experimental investigations. This challenge particularly affects SMEs, but larger companies can also be confronted with similar data problems.

A key aspect of scarce data is that many experiments and data sets are conducted under similar conditions, which means that important variance in the data is missing. However, this variance is crucial to be able to analyse dependencies between input and output variables. To address this problem, AI4ScaDa aims to develop methods and tools that enable the successful use of AI methods even in data-poor environments.