Using Slisemap to interpret physical data
This provides a tool for researchers in physical sciences to interpret black-box models and simulators, but it is incremental as it applies an existing method to new data.
The paper applied Slisemap, a supervised manifold visualization method combining manifold visualization with explainable AI, to physical datasets from physics and chemistry, showing it helps find meaningful information in classification and regression models.
Manifold visualisation techniques are commonly used to visualise high-dimensional datasets in physical sciences. In this paper we apply a recently introduced manifold visualisation method, called Slise, on datasets from physics and chemistry. Slisemap combines manifold visualisation with explainable artificial intelligence. Explainable artificial intelligence is used to investigate the decision processes of black box machine learning models and complex simulators. With Slisemap we find an embedding such that data items with similar local explanations are grouped together. Hence, Slisemap gives us an overview of the different behaviours of a black box model. This makes Slisemap into a supervised manifold visualisation method, where the patterns in the embedding reflect a target property. In this paper we show how Slisemap can be used and evaluated on physical data and that Slisemap is helpful in finding meaningful information on classification and regression models trained on these datasets.