This is an archived version of the Machine Learning Lab website for documentation purposes. The host is in no way affiliated with the University of Freiburg, its Faculty of Engineering or any of its members.

Manuel Blum

Manuel Blum

Machine Learning Lab
University of Freiburg

Room 079/00009
Georges-Koehler-Allee 079
79110 Freiburg im Breisgau

Phone: +49 761 203 8048



  • Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Tobias Springenberg, Manuel Blum, Frank Hutter (2015) Efficient and Robust Automated Machine Learning. In Advances in Neural Information Processing Systems. PDF Bibtex


  • M Duempelmann, S Ewing, M Blum, R Rostek, P Woias, M Riedmiller, A Schulze-Bonhage (2014) Investigation of low complexity seizure detection algorithm for closed loop devices in epilepsy treatment. Clinical Neurophysiology pp. S80. Bibtex


  • Manuel Blum, Martin Riedmiller (2013) Electricity Demand Forecasting using Gaussian Processes. In The AAAI-13 Workshop on Trading Agent Design and Analysis (TADA-13). PDF Bibtex
  • Manuel Blum, Martin Riedmiller (2013) Optimization of Gaussian Process Hyperparameters using Rprop. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. PDF Bibtex


  • Manuel Blum, Jost Tobias Springenberg, Jan Wülfing, Martin Riedmiller (2012) A Learned Feature Descriptor for Object Recognition in RGB-D Data. In IEEE International Conference on Robotics and Automation (ICRA). St. Paul, Minnesota, USA. PDF Bibtex


  • Manuel Blum, Jost Tobias Springenberg, Jan Wülfing, Martin Riedmiller (2011) On the Applicability of Unsupervised Feature Learning for Object Recognition in RGB-D Data. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning. Granada, Spain. PDF Bibtex
  • Manuel Blum, Martin Riedmiller (2011) Q-function Approximation in Batch Mode Reinforcement Learning. In International Workshop on Bio-Inspired Robots. Bibtex
  • Tim Landgraf, Anselm Brachmann, Manuel Blum, Ra{ú}l Rojas (2011) Unsupervised Neural Coding of Nightingale Songs Using Deep Autoencoders. In Computational Neuroscience & Neurotechnology Bernstein Conference & Neurex Annual Meeting. Bibtex


  • CLSquare - Closed Loop Simulation System.
  • libgp - a Gaussian process library for machine learning.
  • nn - a lightweight neural network library using resilient propagation for adapting the weights
  • rpropmatlab - RProp implementation for MATLAB