The DTU:Toolbox™ is a collection of machine learning algorithms implemented mainly for Matlab™. Currently it holds:

  • Independent component analysis (ICA)
  • Artificial neural networks (ANN)
  • Non-negative Matrix Factorization (NMF)

Focus is on developing easy to use algorithms with no or a minimum of parameter tuning. All algorithms come with demonstration scripts that show their use.

The toolbox has been developed by the ISP group at institute Informatics and Mathematical Modelling at the Technical University of Denmark. We gratefully acknowledge the support from the Danish Research Council, the European Union MAPAWAMO project, and National Institutes of Health's Human Brain Project.

All code can be used freely in research and other non-profit applications. If you publish results obtained with the DTU:Toolbox we kindly ask that our and other relevant sources are properly cited. Description, citation and implementation notes for the individual algorithms, are provided with each algorithm. Questions can directed to the [toolbox supervisor].

Before using any of the material provided by the DTU:Toolbox™ the following must be read and accepted: [copyrights and conditions], and for publications cite the general toolbox [citation].

To receive updates and news about the toolbox please subscribe to DTU:Toolbox [mailing list]

Enter Toolbox