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:

lecture
flag A note on Inference for reaction kinetics with monomolecular reactions
as author at  4th International Workshop on Machine Learning in Systems Biology (MLSB), Edinburgh 2010,
79 views
  lecture
flag Bayes Average Case Performance of PAC - Bayes Bounds
as author at  PASCAL Foundations and New Trends of PAC Bayesian Learning, London 2010,
68 views
lecture
flag On the relation between Bayesian inference and certain solvable problems of stochastic control
as author at  Bayesian Research Kitchen Workshop (BARK), Grasmere 2008,
339 views
  lecture
flag Approximate inference for continuous time Markov processes
as author at  Workshop on Approximate Inference in Stochastic Processes and Dynamical Systems, Cumberland Lodge 2008,
587 views
lecture
flag Perturbative Corrections to Expectation Consistent Approximate Inference
as author at  NIPS Workshop on Approximate Bayesian Inference in Continuous/Hybrid Models, Whistler 2007,
143 views
  event
flag NIPS Workshop on Dynamical Systems, Stochastic Processes and Bayesian Inference, Whistler 2006
as organizer at  NIPS Workshop on Dynamical Systems, Stochastic Processes and Bayesian Inference, Whistler 2006,
together with: Cedric Archambeau (organizer), John Shawe-Taylor (organizer),
lecture
flag The Gaussian Variational Approximation of Stochastic Differential Equations
as author at  NIPS Workshop on Dynamical Systems, Stochastic Processes and Bayesian Inference, Whistler 2006,
867 views
  lecture
flag Probabilistic and Bayesian Modelling II
as author at  Spring School in Complexity Science, Southampton 2006,
454 views
lecture
flag Probabilistic and Bayesian Modelling I
as author at  Spring School in Complexity Science, Southampton 2006,
2666 views
  lecture
flag Application of expectation consistent approximate inference
as author at  Workshop on Optimization and Inference in Machine Learning and Physics, Lavin 2005,
75 views
lecture
flag Tractable Inference for Probabilistic Models by Free Energy Approximations
as author at  Machine Learning Workshop, Sheffield 2004,
135 views