Machine Learning Lab
University of Freiburg

Room 079/00010
Georges-Koehler-Allee 079
79110 Freiburg im Breisgau
Germany

Phone: +49 761 203 8040
Email: mblum@informatik.uni-freiburg.de

I am currently working on a BMBF project investigating the neuronal and computational mechanisms of learning, memory and decision-making in biological and artifical agents. My goal is to equip an autonomous robot with minimal implicit knowledge but with a biologically inspired learning and memory architecture allowing it to solve novel tasks of practical relevance. Using neural network approaches, reinforcement learning and machine learning methods, I develop control architectures for autonomous agents based on the biological mechanisms in insects.

• M. Blum, J. T. Springenberg, J. Wülfing and M. Riedmiller. A Learned Feature Descriptor for Object Recognition in RGB-D Data. IEEE International Conference on Robotics and Automation (ICRA). St. Paul, Minnesota, USA, 2012.
• M. Blum, J. T. Springenberg, J. Wülfing and M. Riedmiller. On the Applicability of Unsupervised Feature Learning for Object Recognition in RGB-D Data. NIPS Workshop on Deep Learning and Unsupervised Feature Learning. Granada, Spain, 2011. pdf

• Summer 2012: Special Lecture on Machine Learning (Practice)
• Summer 2011: Special Lecture on Machine Learning (Practice)

• libgp - A Gaussian process library for machine learning