If you are searching for software we used or developed for our papers and the software is not listed above yet, feel free to send an e-mail to Prof. Dr. Bernhard Sick. Your message will be answered as soon as possible.


Software and frameworks

Machine learning applications often require large amounts of training data to achieve good results. While unannotated data can be easily collected, the annotation process is difficult, time-consuming, or expensive for most applications. Active learning can help solve this problem by querying labels for those data samples that improve performance the most. The goal here is for the learning algorithm to perform sufficiently well with fewer annotations.

With this goal in mind, scikit-activeml was developed as a Python module for active learning based on scikit-learn. The project was initiated in 2020 by the Department of Intelligent Embedded Systems at the University of Kassel and is distributed under the 3-Clause BSD license.

The IES research team provides the bibliothek for fast function approximation, which is a class of function approximation tools based on growing and sliding window approaches. The library is written in C++, JAVA and Matlab. It has connections for C and Python. You can use it as a library or purely from source. For more information, read the documentation. The sources can be downloaded here.



  • Native C++ implementations and additional C bindings
  • Native Java implementation
  • Native Matlab implementation
  • Python bindings from the C++ library


Click here to download the waveform data set.

Please contact herwig[at]uni-kassel[dot]de to get access to the EuropeWindFarm dataset.

Please contact herwig[at]uni-kassel[dot]de to get access to the GermanSolarFarm dataset.

Please contact herwig[at]uni-kassel[dot]de to get access to the HessianLoad dataset.

Click here to download the Synthetic Photovoltaic and Wind Power Forecasting data set.

Click here to download the "Multivariate Heterogeneous Time Series Data of a Motor Test Bench" dataset.