Scope:

Machine learning techniques play an increasing role in assisting scientists and engineers in knowledge discovery: obtaining novel information from large, possibly complex data sets. Many practically important tasks, such as weather prediction, financial forecasting, or speech processing, are modelled using time series information. Leveraging explainability or interpretability techniques for knowledge discovery is an active field of research, especially in the domain of time series regression problems. Techniques such as feature attribution are used to gain new insights into the underlying processes being modelled, revealing complex links between modelled parameters.

This workshop provides a forum for discussion and brainstorming ideas related to knowledge discovery in time series data. It is supported by the National Institute for Theoretical and Computational Sciences (NITheCS).

We aim to bring together interested researchers who work in this field (whether NITheCS associates or other interested parties) to demonstrate and discuss recent findings and views.

Booking and registration via the SACAIR site is required.