Effective and efficient time series representation learning poses an important topic for a vast array of applications like, e.g. clustering. Many currently used approaches share the property of being difficult to interpret though. In many areas it is important that intermediate learned representations are easy to interpret for efficient downstream processing.
The following first article part is an attempt to categorize and structure current state of the art (SoA) clustering approaches, making use off of the work of Aljalbout et al. and Min et al. for my current research at TECO Institute from Karlsruhe Institute of Technology regarding missing data imputation in large stock quotation and trade data sets, where clustering would be an obvious first step for retrieving highly correlated quotations or trade movements.
An europython beginner talk on the challenges of developing and integrating a Python based unsupervised learning nlp event detection system into a Java project management software for large EPC projects.