Manfred Opper
homepage: | http://www.ki.tu-berlin.de/menue/about_us/staff/manfred_opper_prof_dr/parameter/en/ |
search externally: | Google Scholar, Springer, CiteSeer, Microsoft Academic Search, Scirus , DBlife |
Description
Statistical Physics, Information Theory, applied Probability and their application to machine learning, disordered materials and other compex systems.
Current projects include:
- Analysis of the generalization ability of neural nets and other learning machines using methods of Statistical Physics.
- General Bounds on entropic error measures in estimating probability distributions.
- Worst Case over sequence prediction.
- Mean Field methods in probabilistic modelling.
- Bayesian approaches to online learning.
- Nonequilibrium dynamics of disordered systems.
- Support Vector Machines
- Population dynamics.
Lectures: