[ KI Home | Members | Courses | Publications ]
|
Artificial
Intelligence Group | Faculty IV
- TU Berlin [ KI Home | Members | Courses | Publications ] |
| 2008 | 2007 | 2006 | 2005 | 2004 | 2003 | 2002 | 2001 | 2000 | 1999 | 1998 | 1997 | 1996 | 1995 | 1990-1994 | 1980-89 |
Cédric Archambeau, Manfred Opper, Yuan Shen, Dan Cornford and John Shawe-Taylor: Variational Inference for Diffusion Processes, 2008, in Advances in Neural Information Processing Systems 20, pages 17-24, MIT Press.
Manfred Opper and Guido Sanguinetti: Variational inference for Markov jump processes, 2008, in Advances in Neural Information Processing Systems 20, pages 1105-1112, MIT Press,
Manfred Opper: A Comparison of Variational and Markov Chain Monte Carlo Methods for Inference in Partially Observed Stochastic Dynamic Systems, 2008, in Journal of Signal Processing Systems SpringerLink Date, pages 1939-8018 (Print) 1939-8115 (Online), Springer New York.
Yuan Shen, Cédric Archambeau, Dan Cornford and Manfred Opper: Variational Markov Chain Monte Carlo for Inference in Partially Observed Nonlinear Diffusions, 2008, in Proceedings of the Workshop Inference and Estimation in Probabilistic Time-Series Models, pages 67-78, Cambridge, UK.
Bert Kappen, Manfred Opper, Riccardo Zecchina and Ruedi Stoop, Editors, Focus on Optimization and Inference in Machine Learning and Physics, 2005, JSTAT.
Dörthe Malzahn and Manfred Opper: A statistical physics approach for the analysis of machine learning algorithms on real data, pdf 2005, in Journal of Statistical Mechanics (JSTAT) .
Tom Heskes, Manfred Opper, Wim Wiegerinck, Ole Winther and Onno Zoeter: Approximate inference techniques with expectation constraints, pdf 2005, in Journal of Statistical Mechanics (JSTAT).
Dan Cornford, Lehel Csató David J. Evans and Manfred Opper: Bayesian Analysis of the Scatterometer Wind Retrieval inverse Problem: Some new Approaches, pdf 2004, in Journal Royal Statistical Society B, pages 1-17.
Manfred Opper and Ole Winther: Expectation Consistent Free Energies for Approximate Inference, pdf 2005, in Advances in Neural Information Processing Systems 17 (to appear).
Manfred Opper and Ole Winther: Variational Linear Response, pdf 2004, in Advances in Neural Information Processing Systems 16, MIT Press.
Manfred Opper and Ole Winther: Approximate Inference in Probabilistic Models, pdf 2004, in Algorithmic Learning Theory, pages 494-504, Springer Verlag.
Dörthe Malzahn and Manfred Opper: An Approximate Analytical Approach to Resampling Averages, pdf 2003, in Journal of Machine Learning Research, pages 1151-1173.
Lehel Csató and Manfred Opper: Sparse Gaussian processes: inference, subspace identification and model selection, pdf 2003, in Proceedings of SYSID 2003, pages 1 - 6.
Dörthe Malzahn and Manfred Opper: A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages, pdf 2003, in Advances in Neural Information Processing Systems 15, pages 327-334, MIT Press.
Manfred Opper: The Complexity of Learning with Supportvector Machines - A Statistical Physics Study, pdf 2003, in Adaptivity and Learning, pages 101-108, Springer Verlag.
Manfred Opper: Statistical Mechanics of Generalization, pdf 2003, in The Handbook of Brain Theory and Neural Networks, 2nd edition, pages 1087-1090, MIT Press.
Lehel Csató and Manfred Opper: Sparse On-Line Gaussian Processes, pdf 2002, in Neural Computation, pages 641-668,
Lehel Csató, Dan Cornford and Manfred Opper: Data Assimilation with Sequential Gaussian Processes, 2002, in Uncertainty in geometrical computation, published by: Kluwer, pages 29-40, Kluwer.
Lehel Csató, Manfred Opper and Ole Winther: TAP Gibbs Free Energy, Belief Propagation and Sparsity, pdf 2002, in Advances in Neural Information Processing Systems 14, pages 657-663, MIT Press.
Manfred Opper and Robert Urbanczik: Asymptotic Universality for Learning Curves of Support Vector Machines, pdf 2002, in Advances in Neural Information Processing Systems 14, pages 479-486, MIT Press.
Dörthe Malzahn and Manfred Opper: Statistical Mechanics of Learning: A Variational Approach for Real Data, pdf 2002, in Phys. Rev. Lett, pages 108302.1-108302.4.
Dörthe Malzahn and Manfred Opper: A Variational Approach to Learning Curves, pdf 2002, in Advances in Neural Information Processing Systems 14, pages 463-469, MIT Press.
Manfred Opper and Ole Winther: Tractable approximations for probabilistic models: The adaptive TAP mean field approach, pdf 2001, in Physical Review Lett, 86, pages 3695-3699.
Manfred Opper and Ole Winther: From Naive Mean Field Theory to the TAP Equations, pdf 2001, in Advanced Mean Field Methods: Theory and Practice, pages 7-20, MIT Press.
Manfred Opper and Ole Winther: Adaptive and Selfaveraging TAP Mean Field Theory, pdf 2001, in Physical Review E, 64, pages 056131.
Manfred Opper and Ole Winther: Adaptive TAP Equations, pdf 2001, in Advanced Mean Field Methods: Theory and Practice, pages 85-97, MIT Press.
Manfred Opper and Robert Urbanczik: Universal learning curves of support vector machines, pdf 2001, in Phys. Rev. Lett, 86: pages 4410-4413.
Manfred Opper and Robert Urbanczik: Support Vector machines learning noisy polynomial rules, pdf 2001, in Physica A, 302: pages 100-118.
Manfred Opper: Learning to Generalize, pdf 2001, in Academic Press, pages 763-775.
Didier Herschkowitz and Manfred Opper: Retarded Learning: Rigorous Results from Statistical Mechanics, pdf 2001, in Phys. Rev. Lett., pages 2174-2177.
Lehel Csató and Manfred Opper: Sparse Representation for Gaussian Process Models, pdf 2001, in Advances in Neural Information Processing Systems 13, pages 444-450, MIT Press.
Lehel Csató, Dan Cornford and Manfred Opper: Online Learning of Wind-Field Models, pdf 2001, in Proceedings of the International Conference on Artificial Neural Networks 2001, pages 300-307, Springer Verlag.
Dörthe Malzahn and Manfred Opper: Learning Curves for Gaussian processes regression: A framework for good approximations, pdf 2001, in Advances in Neural Information Processing Systems 13, pages 273-279, MIT Press.
Dörthe Malzahn and Manfred Opper: Learning curves for Gaussian processes models: Fluctuations and Universality, pdf 2001, in Proceedings of the International Conference on Artificial Neural Networks 2001, pages 271-276, Springer Verlag.
Manfred Opper and David Saad, Editors, 2001, Advanced Mean Field Methods: Theory and Practice, MIT Press.
M. Opper and O. Winther: Gaussian Processes and SVM: Mean Field Results and Leave-One-Out, pdf 2000, in Advances in Large Margin Classifiers, pages 311-326, MIT Press.
B. Lopez and M. Opper: On-line learning from a finite training set: A solvable model , pdf 2000, in Europhys. Lett. pages 275-281.
R. Dietrich, M. Opper and H. Sompolinsky: Statistical Mechanics of SVMs, pdf 2000, in Advances in Large Margin Classifiers, pages 359-367, MIT Press.
L. Csató, E. Fokoue, M. Opper, B. Schottky and O. Winther: Efficient Approaches to Gaussian Process Classification, pdf 2000, in Advances in Neural Information Processing Systems 12, pages 251-257, MIT Press.
Yoav Freund and Manfred Opper: Continuous drifting games, pdf 2000, in Proceedings of the Thirteenth Annual Conference on Computational Learning Theory, pages 126-132, Morgan Kaufmann.
R. Dietrich, M. Opper and H. Sompolinsky: Statistical Mechanics of Support Vector Networks, pdf 1999, Phys. Rev. Lett. , 82 : 2975-2978.
M. Opper and S. Diederich: Replicator Dynamics, 1999, in Proceedings of the Europhysics Conference on Computational Physics CCP 1998, pages 141-144, Elsevier Science.
M. Opper and D. Haussler: Worst Case Prediction over Sequences under Log Loss, pdf 1999, in The IMA Volumes in Mathematics and Its Applications, Volume 107: The Mathematics of Information Coding, Extraction & Distribution, pages 81-90, Springer Verlag.
M. Opper and F. Vivarelli: General Bounds on Bayes errors for regression with Gaussian processes, pdf 1999, in Advances in Neural Information Processing Systems 11, pages 302-308, MIT Press.
M. Opper and O. Winther: Mean field methods for classification with Gaussian processes, pdf 1999, in Advances in Neural Information Processing Systems 11, pages 309-315, MIT Press.
G.F. Trecate, C.K.I. Williams and M. Opper: Finite Dimensional Approximation of Gaussian Processes, pdf 1999, in Advances in Neural Information Processing Systems 11, pages 218-224, MIT Press.
Rainer Dietrich and Manfred Opper: Statistical Mechanics of Learning in the Presence of Outliers, pdf 1998, Journal of Physics A, 31 :9131-9147.
M. Opper: On the Annealed VC Entropy for Margin Classifiers: A Statistical Mechanics Study, pdf 1998, in Advances in Kernel Methods, pages 117-126, MIT Press.
M. Opper: A Bayesian Approach to Online Learning, pdf 1998, in Online Learning in Neural Networks, pages 363-378, Cambridge University Press.
M. Opper: Online versus Offline Learning, pdf 1998, Phil. Mag. B , 77 :1531-1537.
D. Haussler and M. Opper: Metric Entropy and Minimax Risk in Classification, pdf 1997, in Lecture Notes in Computer Science: Studies in Logic and Computer Science, Vol. 1261, pages 212-235, Springer.
D. Haussler and M. Opper: Mutual Information, Metric Entropy, and Risk in Estimation of Probability Distributions, 1997, Annals of Statistics, 26 (6):2451-2492.
Manfred Opper: Regression with Gaussian Processes: Average Case Performance, pdf 1997, in Hong Kong International Workshop on Theoretical Aspects of Neural Computation: A Multi-disciplinary Perspective (TANC 97),, World Scientific.
M. Opper, A. Mietzner and P. Kuhlmann: Convexity, Internal Representations and the Statistical Mechanics of Neural Networks, pdf 1997, Europhys. Lett., 37: 31-36.
M. Opper and O. Winther: A mean field algorithm for Bayes learning in large feedforward neural networks, pdf 1997, in Advances in Neural Information Processing Systems 9, pages 225-231, MIT Press.
M. Opper: Online versus Offline Learning from Random Examples: General Results, pdf 1996, Phys. Rev. Lett., 77 : 4671-4674.
M. Opper and W. Kinzel: Physics of Generalization, 1996, in Physics of Neural Networks III, pages 151-209, by Springer Verlag.
M. Opper and O. Winther: A mean field approach to Bayes learning in feed-forward neural networks, pdf 1996, Phys. Rev. Lett., 76:1964-1967.
D. Haussler and M. Opper: Mutual Information and Bayes Methods for Learning a Distribution, pdf 1995, in Theory of Neural Networks, The Statistical Mechanics Perspective, pages 42-50, World Scientific.
D. Haussler and M. Opper: General Bounds on the Mutual Information Between a Parameter and n Conditionally Independent Observations, pdf 1995, in Proceedings of the Eighth Annual Conference on Computational Learning Theory, pages 402-411, ACM Press.
B. López, M. Schröder and M. Opper: Learning of Correlated Patterns in Perceptrons, 1995, J. Phys. A , 28 :L447.
A. Mietzner, M. Opper and W. Kinzel: Maximal Stability in Unsupervised Learning, 1995, J. Phys. A , 28 : 2785-2797.
M. Opper: Statistical Mechanics of Learning: Generalization, pdf 1995, in The Handbook of Brain Theory and Neural Networks, (1st edition), pages 922-925, MIT Press .
Manfred Opper: Learning in Artificial Neural Networks: The Statistical Mechanics Approach, 1995, in Supercomputing in Brain Reasearch: From Tomography to Neural Networks , pages 321-330, World Scientific.
M. Opper: Statistical Physics Estimates for the Complexity of Feedworward Neural Networks, 1995, Phys. Rev E , 51 :3613-3618.
M. Opper and D. Haussler: General Bounds for Predictive Errors in Supervised Learning, pdf 1995, in Theory of Neural Networks, The Statistical Mechanics Perspective, pages 51-58, World Scientific.
M. Opper and D. Haussler: Bounds for Predictive Errors in the Statistical Mechanics of Supervised Learning, pdf 1995, Phys. Rev. Lett., 75 : 3772-3775.
M. Opper and D. Haussler: Supervised Learning: Information Theoretic Bounds on Predictive Errors, pdf 1995, in Proceedings of the IEEE workshop on Information Theory (ITW'95), pages 6.2.
A. Scharnagl, M. Opper and W. Kinzel: On the Relaxation of Infinite Range Spin Glasses, pdf 1995, J. Phys. A, 28 :5721-5727.
E. Korutcheva, M. Opper and B. López: Statistical Mechanics of the Knapsack Problem, 1994, J. Phys. A, 27 : L645-L650.
M. Opper: Learning and Generalization in a Two--Layer Neural Network: The Role of the Vapnik--Chervonenkis--Dimension, 1994, Phys. Rev. Lett., 72 :2113-2116.
S. Bös, W. Kinzel and M. Opper: The Generalization Ability of Perceptrons with Continuous Outputs, 1993, Physical Review E, 47 : 1384.
M. Opper: Simulating Infinite Systems, 1993, Physica A, 200: 545-551.
M. Opper: Exact Solution to a Toy Random Field Model, 1993, J. Phys. A, 26:L719-L722.
A. Wendemuth, M. Opper and W. Kinzel: The effect of correlations in neural networks, 1993, J. Phys. A, 26:3165-3185.
D. Haussler, M. Kearns, M. Opper and R. E. Schapire: Estimating Average - Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods, 1992, in Advances in Neural Information Processing Systems 4, pages 855-862, Morgan Kaufmann.
M. Opper and S. Diederich: Phase Transition and $1/f$ Noise in a Game dynamical Model, pdf 1992, Phys. Rev. Lett., 69 ( ): 1616-1619.
Manfred Opper: Physik lernender Netzwerke (physics of learning networks), 1992, Physikalische Blätter, 48 :569-574.
H. Schwarze and M. Opper and W. Kinzel: Generalization in a two-layer network, 1992, Phys. Rev. A, 46: 6185-6188.
H.S. Seung, M. Opper and H. Sompolinsky: Query by committee, pdf 1992, in Proceedings of the Fifth Annual Conference on Computational Learning Theory, pages 287-294, ACM Press.
H. Bolterauer and M. Opper: The Quantum Lifetime of the Davydov Soliton, 1991, Z. Phys. B, 82 : 95-103.
R. D. Henkel and M. Opper: Parallel Dynamics of the Neural Network with Pseudoinverse Coupling Matrix, 1991, J. Phys A, 24: 2201-2218.
W. Kinzel and M. Opper: Dynamics of Learning, 1991, in Physics of Neural Networks, pages 149-171, Springer Verlag.
M. Opper and D. Haussler: Calculation of the Learning Curve of Bayes Optimal Classification Algorithm for Learning a Perceptron With Noise, 1991, in Proceedings of the Fourth Annual Conference on Computational Learning Theory, pages 75-87, Morgan Kaufmann.
M. Opper and D. Haussler: Generalization Performance of Bayes Optimal Prediction Algorithm for Learning a Perceptron, 1991, Phys. Rev. Lett., 66: 2677-2680.
H. Köhler, S. Diederich, W. Kinzel and M. Opper: Learning algorithm for a Neural Network with binary synapses, 1990, Zeitschrift f"ur Physik B,78 : 333-342.
M. Opper, W.Kinzel, J. Kleinz and R. Nehl: On the Ability of the Optimal Perceptron to Generalize, 1990, J. Phys. A, 23 : L581-L586.
H. Bolterauer and M. Opper: Nonlinear Excitations in the Low Temperature Region of the Classical Toda Lattice, 1981, Phys. Lett. A, 83: 69-70.
H. Bolterauer and M. Opper: Solitons in the Statistical Mechanics of the Toda Lattice, 1981, Z. Phys. B, 41: 155-161.
M. Opper: Analytical Solution of the Classical Bethe-Ansatz Equation for the Toda Chain, 1985, Phys. Lett. A, 112: 201-203.
H. Bolterauer, R. D. Henkel and M. Opper: Resonant and Quasiclassical Excitations of Solitons in the Alpha- Helix, 1986, in Structure, Coherence and Chaos in Dynamical Systems, pages 625-631, Manchester University Press.
S. Diederich, M. Opper, R. D. Henkel and W. Kinzel: Learning by Error Correction in Spin Glass Models of Neural Networks, 1988, in Computer Simulations in Brain Science, Cambridge University Press.
M. Opper: Solution of a random Chain Problem - an Approach using Canonical Variables of an Integrable System, 1986, J. Phys. A, 19: L1073-L1077.
S. Diederich and M. Opper: Learning of Correlated Patterns in Spin- Glass Networks by Local Learning Rules, 1987, Phys. Rev. Lett., 58:949-952.
Manfred Opper: Eine neue Methode zur L"osung eindimensionaler Modelle mit Unordnung (A new method for solving one dimensional models with disorder), 1987, Ph. D. thesis, Giessen University, Germany.
M. Opper, S. Diederich and J. K. Anlauf: Statistical Mechanics of Learning in Neural Network Models, 1987, in Chaos and Complexity, pages 219-223, World Scientific.
M. Opper: Learning Times of Neural Networks: Exact Solution for PERCEPTRON Algorithm, 1988, Phys. Rev. A (Rapid Comm.), 38( ): 3824-3826.
M. Opper, S. Diederich and J.K. Anlauf: Statistical Mechanics of Learning in Neural Network Models, 1988, in Neural Networks from Models to Applications, pages 235-243, I.D.S.E.T., Paris.
S. Diederich and M. Opper: Replicators with Random Interactions- a Solvable Model, 1989, Phys. Rev. A (Rapid Comm.), 39 :4333.
W. Krauth and M. Opper: Critical Storage Capacity of the Neural Network, 1989, J. Phys. A, 22: L519-L523.
M. Opper: Pattern Recognition, 1989, in Computersimulations in Physics, 20. IFF- Summer School KFA Juelich, pages 29.1-29.12.
M. Opper: Learning Rules and Learning Times in Neural Networks, 1989, in Dynamics of Networks, pages 66-75, Akademie Verlag Berlin.
M. Opper: Learning in Neural Networks: Solvable Dynamics, 1989, Europhys. Lett., 8: 389-392.
M. Opper, J. Kleinz, H. Koehler and W. Kinzel: Basins of Attraction near the Critical Storage Capacity for Neural Networks with Constant Stabilities, 1989, J. Phys. A, 22 : L407-L411.