Professor Manfred Opper

Manfred Opper

Institute of Metabolism and Systems Research
Professor of Machine Learning

Contact details

Centre for Systems Modelling and Quantitative Biomedicine
University of Birmingham
B15 2TT

Professor Manfred Opper is interested in the development and the theoretical analysis of methods for probabilistic inference in machine learning using techniques of statistical mechanics and statistics. In recent years he has worked especially in the area of data assimilation, where he has developed approximations for inference in stochastic differential equations, Markov jump processes and dynamical processes on large networks. He also works on the relation between inference and optimal stochastic control and on the application of random matrix theory to machine learning algorithms.  He has over 170 publications, mostly in applications of statistical mechanics and related probabilistic methods to problems of machine learning and other complex systems. He is a member of the editorial board of Journal of Statistical Mechanics.


• Habilitation degree in Theoretical Physics, University of Giessen (Germany) 1990
• Dr. rer. nat. in Physics, University of Giessen (Germany) 1987
• Diploma in Physics, University of Giessen (Germany) 1983


Professor Manfred Opper has a  PhD in Physics and a Habilitation degree in Theoretical Physics from the University of Giessen, Germany. In 1992 he received the Physics Prize of the German Physical Society for his work on learning in neural networks. In 1994 he was awarded a Heisenberg fellowship from the German research foundation, DFG. He has held faculty positions at the Neural Computing Research Group at Aston University in Birmingham UK, and at the ISIS group of Southampton University. Manfred Opper became a professor for Methods of Artifical Intelligence at Technical University of Berlin in 2006.

• Professor of Machine Learning, University of Birmingham (UK) 2020
• Professor, Institute for Software Engineering and Theoretical Computer Science , TU Berlin (Germany) 2006
• Professor (personal chair), School of Electronics and Computer Science, University of Southampton (UK), 2005
• Reader, School of Engineering and Applied Science, Aston University, Birmingham (UK) 1997


• Statistical Inference for stochastic processes (stochastic differential equations and point processes)
• Applications of random matrix theory in machine learning
• Stochastic dynamics on large networks
• Approximate Bayesian inference for large probabilistic models
• Nonparametric Bayesian models
• Probabilistic inference and optimal control
• Computational learning theory
• Analysis of machine learning problems and neural network models using methods of statistical mechanics


Batz, P., Ruttor, A., Opper, M. (2018).  Approximate Bayes learning of stochastic differential equations. Phys. Rev E, 98:022109

Cseke, B., Opper, M., Sanguinetti, G. (2013). Approximate inference in latent Gaussian-Markov models from continuous time observations. Advances in Neural Information Processing Systems, 26:971-979.

Opper, M., Paquet U., Winther O. (2013). Perturbative corrections for approximate inference in Gaussian latent variable models. Journal of Machine Learning Research, 14:2857-2898.

Archambeau, C., Opper, M., Shen, Y., Cornford, D., Shawe-Taylor, J. (2008). Variational inference for diffusion processes.

Archambeau, C., Opper, M. (2008).The variational Gaussian approximation revisited. Neural Computation}, 21:786-92.

Opper, M., Winther O. (2005). Expectation consistent approximate inference. Journal of Machine Learning Research,
6 :2177-2204.

Csató, L., Opper, M. (2002). Sparse on-line Gaussian processes. Neural Computation, 14:641-668.

Opper, M., Winther O. (2001). Tractable approximations for probabilistic models: The adaptive TAP mean field approach. Phys. Rev. Lett., 86:3695-3699.

Haussler, D., Opper, M. (1997). Mutual information, metric entropy, and risk in estimation of probability distributions. Annals of Statistics, 26:2451-2492.

H. S. Seung; M. Opper and H. Sompolinsky. (1992) Query by committee. In Proceedings of the Fifth Annual Conference on Computational Learning Theory, pages 287-294. ACM Press.

View all publications in research portal