My current research as a postdoc at the Max Planck Institute for Biological
Cybernetics in Tübingen, Germany, focuses on causal inference.
I have done my PhD research at the Radboud University Nijmegen, under supervision
of Prof. Dr. H.J. Kappen, on approximation
techniques for calculating probabilities in large, complex probabilistic models.
-
Distinguishing between cause and effect
J. M. Mooij, D. Janzing
-
Identifying confounders using additive noise models
D. Janzing, J. Peters, J. M. Mooij, B. Schölkopf
Proceedings of the 25th Annual Conference on Uncertainty in Artificial Intelligence (UAI-09) (
UAI 2009)
-
Regression by dependence minimization and its application to causal inference
J. M. Mooij, D. Janzing, J. Peters, B. Schölkopf
Proceedings of the 26th Annual International Conference on Machine Learning (ICML 2009) (
ICML 2009)
-
Nonlinear causal discovery with additive noise models
P. Hoyer, D. Janzing, J. Mooij, J. Peters, B. Schölkopf
Advances in Neural Information Processing Systems 21 (
NIPS*2008)
(Corollary 2 which appeared in a previous version of this paper has been removed because it contained an error)
-
Bounds on marginal probability distributions
J.M. Mooij, H.J. Kappen
Advances in Neural Information Processing Systems 21 (
NIPS*2008)
-
Understanding and Improving Belief Propagation
J.M. Mooij
PhD thesis May 7, 2008
-
Sufficient Conditions for Convergence of the Sum-Product Algorithm
J.M. Mooij, H.J. Kappen
IEEE Transactions on Information Theory 53(12):4422-4437, Dec. 2007
-
Truncating the Loop Series Expansion for Belief Propagation
Vicenç Gómez, J. M. Mooij, H. J. Kappen
-
Loop Corrections for Approximate Inference on Factor Graphs
Joris M. Mooij, Hilbert J. Kappen
-
Inference in the Promedas medical expert system
Bastian Wemmenhove, Joris M. Mooij, Wim Wiegerinck, Martijn Leisink, Hilbert J. Kappen, Jan P. Neijt
Proceedings of the 11th Conference on Artificial Intelligence in Medicine (
AIME 07)
-
Loop Corrected Belief Propagation
J.M. Mooij, B. Wemmenhove, H.J. Kappen, T. Rizzo
Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics (
AISTATS-07)
-
Sufficient conditions for convergence of Loopy Belief Propagation
J.M. Mooij, H.J. Kappen
Proceedings of the 21th Annual Conference on Uncertainty in Artificial Intelligence (
UAI-05)
-
On the properties of the Bethe approximation and Loopy Belief Propagation on binary networks
J.M. Mooij, H.J. Kappen
-
Validity Estimates for Loopy Belief Propagation on Binary Real-world Networks
J.M. Mooij, H.J. Kappen
Advances in Neural Information Processing Systems 17 (
NIPS*2004)
-
Quantitative Imaging through a Spectrograph. 1. Principles and Theory
René Tolboom, Nico Dam, Hans ter Meulen, Joris Mooij, Hans Maassen
libDAI is a free/open source C++ library (licensed under GPL) that provides implementations of various (deterministic) approximate inference methods for discrete graphical models. libDAI supports arbitrary factor graphs with discrete variables (this includes discrete Markov Random Fields and Bayesian Networks).
For more information, see the special page on libDAI. Other licensing options are available upon request.
Selection of slides for talks given at conferences or workshops.
libDAI - a FOSS library for Discrete Approximate Inference methods
(presented at MLOSS 2008).
