Time series data have been used in many applications in healthcare, such as the diagnosis of a disease, prediction of disease progression, clustering of patient groups, online monitoring and dynamic treatment regimes, to name a few. More and more methods build on representation learning to tackle these problems by first learning a (typically low-dimensional) representation of the time series and then use the learned representation for the corresponding downstream task.Machine learning (ML) provides a powerful set of tools for time series data, but its applicability in healthcare is still limited. As a result, the potential of time series analysis cannot be fully realised currently. Furthermore, it is expected that in the coming years, the availability and nature of time series data will continue to increase. These data could support all components of healthcare to benefit everyone. Handling time series data is a challenge, especially in the medical domain, for reasons such as the following:- Labeling, in general and in particular of long-term recordings, is a nontrivial task requiring appropriate experts like clinicians who are restricted in their time- Time series data acquired within real-life settings and novel measurement modalities are recorded without supervision having no labels at all- The high-dimensionality of data from multimodal sources- Missing values or outliers within acquired data or irregularity of measured dataThis workshop focuses on these aspects and the potential benefits of integrating representation learning in time series applications. Our goal is to encourage a discussion around developing new ideas towards representation learning complemented with robust, interpretable, and explainable approaches which can provide a medical expert with more information than just a prediction result. We want to encourage participants to tackle challenges in the time series domain.