Bert Kappen

Bert (HJ) Kappen





The physics of inference and control

Keywords: Bayesian inference, learning and reasoning, stochastic control theory, neural networks, statistical physics

One of the marked differences between computers and animals is the ability of the latter to learn and flexibly adapt to changing situations. Whereas computers need to be programmed with provisions for all possible future circumstances, the brain adapts its 'program' when needed, striking a remarkable balance between flexibility to adapt on the one hand and persistence by re-using pre-learned facts and skills on the other. This is commonly referred to as intelligent behavior. Particular examples of intelligence are pattern recognition, learning and memory, reasoning, planning and motor control.

The question how intelligence arises and how it is computed in the animal brain is not well understood. One can try to reproduce intelligence in artificial systems and the problems of how intelligence is encoded in the brain and how it can be created artificially in computers are clearly related. In addition to being an important intellectual challenge in itself, artificial intelligence research also has clear practical implications. We currently witness an explosion of applications in machine learning - the formal study of how machines learn - in for instance robotics and data analysis.

Due to the essential roles that noise and uncertainty play in perception and learning, a useful way to model intelligence is to use probability models. In the mid 90s, the fields of analog and digital computing as separate approaches to model intelligence, have begun to merge using the idea of Bayesian inference: One can generalize the logic of digital computation to a probabilistic calculus, embodied in a so-called graphical model. Similarly, one can generalize dynamical systems to stochastic dynamical systems that allow for a probabilistic description in terms of a Markov process. The Bayesian paradigm has greatly helped to integrate different schools of thought in particular in the field of artificial intelligence and machine learning but also provides a computational paradigm for neuroscience.

My research is dedicated to the design of efficient and novel computational methods for Bayesian inference and stochastic control theory using ideas and methods from statistical physics. These novel methods are used by me and by others in artificial intelligence research and computational models of brain function.

Bayesian Inference

Bayesian models are probability models and the typical computation, whether in the context of a complex data analysis problem or in a stochastic neural network, is to compute an expectation value, which is referred to as Bayesian inference. Bayesian inference is intractable, which means that computation time and memory use scale exponentially with the problem size. However, many methods exist to compute these quantities approximately. Most of these methods origin from statistical physics, such as the mean field method, belief propagation or Monte Carlo sampling. Application of these methods to machine learning problems is challenging and an active field of research to which I have made several contributions. Current projects focus on the application of these ideas in concrete problems:

Control theory

Control theory is a theory from engineering that gives a formal description of how a system, such as a robot or animal, can move from a current state to a future state at minimal cost, where cost can mean time spent, or energy spent or any other quantity. Control theory is used traditionally to control industrial plants, airplanes or missiles, but is also the natural framework to model intelligent behavior in animals or robots. The mathematical formulation of deterministic control theory is very similar to classical mechanics. In fact, classical mechanics can be viewed as a special case of control theory. Stochastic control theory uses the language of stochastic differential equations. For a certain class of stochastic control problems, the solution is described by a linear partial differential equation that can be solved formally as a path integral. This so-called path integral control method provides a deep link between control, inference and statistical physics. This statistical physics view of control theory shows that qualitative different control solutions exist for different noise levels separated by phase transitions. The control solutions can be computed using efficient approximate inference methods such as Monte Carlo sampling or deterministic approximation methods. The path integral control theory is successfully being used by leading research groups in robotics world wide. For more information see the path integral control theory page.

Computational neuroscience

Another line of research, that was started in 2000 and is still continued, is on the effect that short-term synaptic plasticity has on memory storage. The common understanding of long term memory is that it is stored in the synaptic connections between neurons in such a way that memory retrieval occurs as the relaxation of the neural activity to a constant spiking pattern, that represents the memory. This idea was put forward by Hopfield (1982) and others as the attractor neural network. Synaptic dynamics challenges this mechanism, since persistent pre-synaptic activity typically weakens the synaptic strength. The inclusion of short-term synaptic plasticity in an attractor neural network make memories metastable states that rapidly switch from one state to the next, depending on the sensory context. This work provides some insights on the puzzle how the brain, viewed as a dynamical system, is able to build stable representations of the world and at the same time is capable to effortlessly switch between them. With (J. Torres, University of Granada).

Data analysis

Modern experimental neuro-science has been revolutionarized by sophisticated measurement equipment, such as fMRI, MEG and others. Also, the advances in EEG measurement systems has accelerated the research on Brain Computer Interfaces. Thirdly, research tools in genetics have led to an explosion of DNA and expression data. These massive data sets require advanced data analysis tools. Machine learning methods (kernel methods, sparse dimension reduction methods, ICA, Bayesian approaches) provide the most promising approach to analyze these data.

Brain Computer Interface

Since 2009, I have started research on the design of an adaptive BCI system, based on the idea that subjects will be surprised when the BCI output differs from their expectation. This surprise is measurable as a so-called error potential. The detection of the error potential can be used to adapt the BCI device, using the perceptron learning rule (V. Gomez and A. Llera with O. Jensen, Donders Neuro-imaging Center).

Applications

Bayesian methods have a big potential for immediate application in areas outside science. There is a long-standing and quite unique tradition in the SNN group to build such application together with her spin-off companies Smart Research and Promedas. Here are a few examples:

Genetic inference

We have applied an advanced approximate inference method (the Cluster Variation Method) to construct haplotypes in complex pedigrees. The method was shown to outperform the state-of-the-art Monte Carlo sampling approach on a subset of problems. The software is publicly available. Contact Kees Albers for details caa at sanger dot ac dot uk.
Aladin is a software tool for performing efficient linkage analysis of a small number of distantly-related individuals. It estimates multipoint IBD probabilities and parametric LOD scores. Contact Kees Albers for details caa at sanger dot ac dot uk.

Oil exploration

For Shell, we built a petrophysical expert system. It estimates the type of soil and the probability that it contains oil, gas or other valuable minerals, based on drilling measurements. The system is based on a Bayesian network where the probability computation is done using a Monte Carlo sampling method. See Smart Research for further details and other products.

Victim identification

For the Netherlands Forensic Institute, we are building a victim identification system by matching of their DNA profiles against the Pedigrees of Relatives from Missing Person's DNA profiles in large databases, using a Bayesian network. See Bonaparte for further details.

Promedas

We have built the world largest and most up-to-date medical expert system for diagnostic advice in internal medicine. The system is being commercialized by Promedas bv. The system is since end 2008 operational at the Utrecht academic hospital. See Promedas for further details.

Wine and food

We have built a system that selects the most appropriate wines to combine with your food Wine wine wine.

Teaching

Inleiding Machine Learning BA
Computational Neuroscience MA
Machine Learning MA
Introduction to Pattern Recognition MA
Computational Physics MA
Information, Physics, and Computation MA

Short course on control theory, ACNS
Short course on machine learning, Pompeu Fabra spring 2003
Short course on control theory, Madrid fall 2010
Short course on control theory, UCL 2011
Short course on control theory, Madrid 2012
Tutorial ICTP Summer school Machine Learning, Trieste 2012
Short course on control theory, Madrid 2013
Tutorial ICTP Spring College on Physics of Complex systems, Trieste May-June 2013
Short course on control theory, Madrid 2014

Introduction to Biophysics BA (discontinued)
Neural networks and Information theory BA (discontinued, content moved to Inleiding Machine Learning BA from 2012-2013)
Neurophysics BA (discontinued, content moved to Computational Neuroscience MA from 2013-2014)
Neurophysics MA (discontinued)

Master Projects

Here are examples of possible master projects for prospective students. Bachelor projects could be defined as downsized versions of these projects.

Cooperative behavior in multi agent systems

Humans and animals cooperate to achieve certain tasks. Examples are team sports, such as soccer, or bees searching for food. Cooperative behaviour can be modelled as a stochastic optimal control problem. In the centralized formulation of the problem, a single multi-agent control problem is solved by a 'commander'. The commander is assumed to observe the current position and velocities of all agents and have detailed knowledge of their internal dynamics. The solution to the optimal control problem yields the next action of all agents. In the decentralized formulation of the problem there is no commander. Instead, each agent solves its own control problem and computes its own next action. For this, the agent needs to observe the other agents current position and velocities and in addition make assumptions about the future trajectories of all other agents. In our previous research, we have solved the centralized and decentralized control problem in the context of unmanned aerial vehicles (uav's) in a simple setting. See control page. In this project, the student will extend this line of research to include more realistic sensing and communication modalities.

Stochastic optimal control for option pricing

Options are financial derivatives that are traded at an exchange. The option is the right to buy or sell an asset, such as oil, at a future time at a fixed price. The value of the option is given by a complex formula that can only be computed explicity in very simple cases. In general, the option price is estimated using Monte Carlo sampling. This computation is time-consuming and much effort is made to accelerate the computation. The option pricing problem can be formulated as a stochastic optimal control problem. The optimal sampling strategy coincides with the optimal control solution to the problem. A type of importance sampling can be implemented using suboptimal controls. In this project, the student will develop novel importance sampling methods to compute the option price using feed-back controllers.

Sparse regression with the Garrote

Standard learning problems are to explain a dependent variable ('the output') in terms of independent variables ('the inputs'). In many learning problems, the number of input variables is large compared to the number of available data samples. Examples are found in genetics, neuro imaging and in general in many pattern recognition problems. In order to obtain a reasonable solution in these cases, the problem needs to be regularized, typically by adding a constraint that enforces a solution with small norm. In addition often a sparse solution is desired, which explains the output in terms of a (small) subset of the input variables. The Lasso method is a sparse regression method that uses an L1 norm as regularizer. The Lasso is very fast and can be applied to very large problems. However, the method suffers from 'shrinkage' which means that in certain cases the wrong inputs are identified. Ideally, one would use a regularizes which penalizes the number of inputs rather than their strength. This is achieved using the so-called L0 regularizer. However, to find the solution in this case is significantly more difficult. Examples of approaches are Monte Carlo methods or the variational garrote. All sparse methods suffer from strongly correlated inputs. Examples are the spatial correlations between nearby genetic measurements, or pixels in images. In this project, the student will extend the variational garrote to take these correlations into account and to demonstrate the improved performance on neuro-imaging or genetic data.

Contact information

SNN Machine Learning
Radboud University
Huygensgebouw 00.829
Heyendaalseweg 135
NL 6525 AJ Nijmegen
The Netherlands
+31 24 3614241 (phone)
b.kappen-at-science-dot-ru-dot-nl

Recent meetings organized

NIPS Workshop Probabilistic optimal control, Whistler 2009
SNN Symposium Intelligent Machines, Nijmegen 2010
School on large scale problems in machine learning and workshop on common concepts in machine learning and statistical physics, ICTP Trieste 2012
Workshop on the statistical physics of inference and control theory, Granada 2012 website and videolectures
LSOLDM 2013
NIPS 2013 Workshop Planning with Information Constraints for control, reinforcement learning, computational neuroscience, robotics and games
LSOLDM 2014
Intelligent Machines 2015

Organizations and collaborations

Foundation for Neural Networks (SNN)
Ruedi Stoop (ETH) and the European Center for Recreational Physics
Granada computational neuroscience and neurophysics group
Pattern Analysis, Statistical Modelling and Computational Learning (Pascal 2)
Visiting professor at Gatsby Computational Neuroscience Unit, University College London

Current group members

Wim Wiegerinck is senior researcher and is working on approximate inference, genetic inference and various applications and is associate director of Smart Research bv
Sep Thijssen is a PhD student funded by Thales Nederland and on the Complacs project, working on application of stochastic optimal control methods for multi-agent systems
Hans Ruiz is a PhD student on the NETT project. He works on the application of stochastic optimal control methods in neuroscience for multi-agent systems
Dominik Thalmeier is a PhD student on the NETT project. He works on the application of stochastic optimal control methods in neuroscience for multi-agent systems
Willem Burgers is programmer for Smart Research bv

Former group members

Tom Heskes (Radboud University Nijmegen) was PhD student and postdoc on online learning.
Martijn Leisink (D66) was PhD student and postdoc on approximate inference
Taylan Cemgil (Bogazici University, Turkey) was PhD student on time-series modeling of music
Joris Mooij was PhD student on approximate inference.
Kees Albers was PhD student and postdoc on approximate inference methods for genetic linkage analysis. Kees was 4 years at Sanger Institute, Cambridge UK and is since 2012 at Human Genetics in Nijmegen.
Bram Kasteel was Bachelor student on the topic of multi-agent control
Stijn Tonk was Master student on the topic of multi-agent control
Ender Akay was programmer for Smart Research bv and Promedas bv
Gulliver de Boer was Bachelor student on the topic of multi-agent control applied to poker
Max Bakker was a Bachelor student on the topic of multi-agent systems
Ben Ruijl was a Bachelor student on the topic of multi-agent systems
Henk Griffioen was Master student on the topic of genetic association studies
Bart van den broek was PhD student on the topic of stochastic optimal control theory
Mohammad Azar was PhD student on the topic of reinforcement learning, now at Carnegie Mellon University
Patrick Lessmann was PhD student on the topic of stochastic optimal control in the CompLACS (EU FP7) project.
Elena Zavgorodnyaya was Master student on the topic of Brain Computer Interfaces.
Martin Mittag was a master student on the topic of stochastic optimal control theory with neural networks
Dick van den Broek was a master physics student on the topic of multi-agent systems
Bram Kasteel was a master physics student on the topic of stochastic optimal control theory
Christiaan Schoenaker was a master physics student on the topic of Super Modeling by combining imperfect models (SUMO)
Jonas Ahrendt was a Artificial Intelligence student on the topic of genetic pedigrees and Bonaparte
Joris Bukala was a bachelor physics student on the topic of Monte Carlo methods
Gulliver de Boer was a master physics student on the topic of genetic linkage analysis with Gaussian Process Regression and implementation on GPUs
Vicenç Gómez was postdoc on approximate inference and stochastic optimal control in the CompLACS (EU FP7) project, now at Universidad Pompeu Fabra in Barcelona
Kevin Sharp was a postdoc on a project to develop Bayesian Gaussian process methodes for genetic association studies, now at Oxford University
Joris Bierkens was postdoc on the topic of stochastic optimal control in the CompLACS (EU FP7) project, now at Warwick University
Takamitsu Matsubara is assistant professor of robotics at the Nara Institue of Science and Technology on sabatical leave in our group in 2013
Alberto Llera was PhD student on the topic of Brain Computer Interfaces, now postdoc with Christian Beckman at the Donders Center for Imaging

Externally funded projects

BrainGain (Smart mix)
Genetic association study using machine learning methods (Donders internal round)
Brain imaging, genetics and psychiatry using machine learning methods (NWO Cognition)
Multi-agent systems (with Thales D-Cis lab)
Bonaparte (Smart Research with the Dutch Forensic Institute)
Bovinose (Smart Research, EU FP7)
CompLACS (EU FP7)
SUMO (EU FP7)
NETT
Decentralized UAV control (with TU Delft Micro Air Vehicle laboratory)

Vacancies

There are currently no vacancies ckv.docx

Publications

2014
Chernyak V., Chertkov, M, Bierkens J., Kappen H.J.
Stochastic optimal control as non-equilibrium statistical mechanics: calculus of variations over density and current.
Journal of Physics A: Mathematical and Theoretical as a Fast Track Communication, vol. 47, no. 2, pp. 022001, 2014

Llera A., G贸mez V., Kappen H.J.
Adaptive multi class classification on bci.
Neural Computation, pp. 1-20, 2014

Matsubara T., G贸mez V., Kappen H.J.
Latent kullback leibler control for continuous-state systems using probabilistic graphical models.
Proceedings UAI, vol. 30, pp. 1-12, 2014

G贸mez V., Nijman G., Peters J., Kappen H.J.
Policy search for path integral control .
LNAI conference proceedings, pp. 1-16, 2014

Bierkens J., Kappen H.J.
Explicit solution of relative entropy weighted control.
Systems and Control Letters, pp. 1-16, 2014

2013
Kappen H.J., G贸mez V.
The variational garrote.
Machine Learning Journal, pp. 1-26, 2013

Gheshlaghi Azar M., Munos R., Ghavamzadaeh M., Kappen H.J.
Speedy q-learning: a computationally efficient reinforcement learning algorithm with a near optimal rate of convergence.
Journal of Machine Learning Research, 2013

Gheshlaghi Azar M., Munos R., Kappen H.J.
Minimax pac bounds on the sample complexity of reinforcement learning with a generative model.
Machine Learning Journal, vol. 91, no. 3, pp. 325-349, 2013

Bierkens J., Chertkov, M, Kappen H.J.
Linear pdes and eigenvalue problems corresponding to ergodic stochastic optimization problems on compact manifolds.
pp. 1-16, 2013

Torres J.J., Kappen H.J.
Emerging phenomena in neural networks with dynamic synapses and their computational implications.
Frontiers in Computational Neuroscience, vol. 7, no. 30, pp. 1-13, 2013

Wiegerinck W.A.J.J., Burgers W.G., Kappen H.J.
Bayesian networks, introduction and practical applications.
Handbook on Neural Information Processing, vol. 49, pp. 401-431, 2013

Kappen H.J., G贸mez V.
Stochastic optimal control and sensori-motor integration.
Technical Report, pp. invited paper, 2013

Kappen H.J.
Comment: causal entropic forces.
Technical Report, pp. http://arxiv.org/abs/1312.4185, 2013

Llera A., G贸mez V., Kappen H.J.
Clustered common spatial patterns.
TOBI Workshop IV, pp. 117-119, 2013

Llera A., G贸mez V., Kappen H.J.
Is task selection a solution for bci illiteracy?.
Journal of Neural Engeneering, 2013

Thijssen S.A., Kappen H.J.
Stochastic path integral control.
International Journal of Control, 2013

2012
Kappen H.J., G贸mez V., Opper M.
Optimal control as a graphical model inference problem.
Machine Learning, vol. 87, no. 2, pp. 159-182, 2012

G贸mez V., Kappen H.J., Litvak N., Kaltenbrunner A.
A likelihood-based framework for the analysis of discussion threads.
World Wide Web, pp. 1-31, 2012

Llera A., G贸mez V., Kappen H.J.
Adaptive classification on brain computer interfaces using reinforcement signals.
Neural Computation, vol. 24, no. 11, pp. 2900-2923, 2012

Gheshlaghi Azar M., Munos R., Kappen H.J.
On the sample complexity of reinforcement learning with a generative model.
Proceedings of the International Conference on Machine Learning Learning, vol. 29 th, pp. 1-11, 2012

Torres J.J., Kappen H.J.
Emerging phenomena in neural networks with dynamic synapses and their computational implications.
Frontiers in Neuroscience, 2012

Mejias FF., Kappen H.J., Longtin A., Torres J.J.
Short-term synaptic plasticity and heterogeneity in neural systems.
Granada Seminar AIP Proceedings 2013, 2012

Gheshlaghi Azar M., G贸mez V., Kappen H.J.
Dynamic policy programming.
Journal of Machine Learning Research, no. 13, pp. 3207-3245, 2012

G贸mez V., Chertkov, M, Backhaus S., Kappen H.J.
Learning price-elasticity of smart consumers in power distribution systems..
SmartGrid Comm 2012, Symposium ion Architectures and Models for the SmartGrid, pp. invited paper, 2012

Tramper J.J., Broek J.L. van den, Kappen H.J., Gielen C.C.A.M.
Time-integrated position error accounts for sensorimotor behavior in time-constr ained tasks..
Plos One, vol. 7, no. 3, pp. e33724, 2012

2011
Llera A., Gerven M van, G贸mez V., Jensen O., Kappen H.J.
On the use of interaction error potentials for adaptive brain computer interfaces.
Neural Networks, vol. 24, pp. 1120-1127, 2011

Kappen H.J.
Optimal control theory and the linear bellman equation.
Inference and Learning in Dynamic Models, pp. 363-387, 2011

Tramper J.J., Broek J.L. van den, Wiegerinck W.A.J.J., Kappen H.J., Gielen C.C.A.M.
Stochastic optimal control predicts human motor behavior in time-constrained sensorimotor tasks.
Biological Cybernetics, pp. xx, 2011

Gheshlaghi Azar M., Munos R., Ghavamzadaeh M., Kappen H.J.
Speedy q-learning.
NIPS 2011, Advances in Neural Information Processing Systems 24, vol. 25, pp. 2411--2419, 2011

Bierkens J., Kappen H.J.
Online solution of the average cost kullback-leibler optimization problem.
NIPS 2011, 4th International Workshop on Optimization for Machine Learning, vol. 25, pp. 1-6, 2011

G贸mez V., Kappen H.J., Kaltenbrunner A.
Modeling the structure and evolution of discussion cascades..
Proceedings of the 22nd ACM Conference on Hypertext and Hypermedia, vol. 22, pp. 181-190, 2011

Broek J.L. van den, Wiegerinck W.A.J.J., Kappen H.J.
Stochastic optimal control of state constrained systems.
International Journal of Control, vol. 84, no. 3, pp. 597-615, 2011

Gheshlaghi Azar M., G贸mez V., Kappen H.J.
Dynamic policy programming with function approximation.
JMLR: Workshop and Conference Proceedings: AISTATS 2011, vol. 15, pp. 119-127, 2011

Kappen H.J.
Machines - now with intelligence.
Donders Institute for Brain, Cognition and Behaviour, no. 17, pp. 4-5, 2011

2010
Wiegerinck W.A.J.J., Kappen H.J., Burgers W.G.
Bayesian networks for expert systems, theory and practical applications.
Interactive Collaborative Information Systems, vol. SCI 281, pp. 547-578, 2010

Burgers W.G., Wiegerinck W.A.J.J., Kappen H.J., Spalburg M.
A bayesian petrophysical decision support system for estimation of reservoir compositions.
Expert Systems With Applications, vol. 37, no. 12, pp. 7526-7532, 2010

G贸mez V., Kappen H.J., Chertkov, M
Approximate inference on planar graphs using loop calculus and belief propagation.
Journal for Machine Learning Research (JMLR), vol. 11, pp. 1273-1296, 2010

Mensink T., Verbeek J., Kappen H.J.
Ep for efficient stochastic control with obstacles.
ECAI, pp. 1-6, 2010

Kappen H.J., Tonk S.
Optimal exploration as a symmetry breaking phenomenon.
no. TR1001, pp. 1-5, 2010

Broek J.L. van den, Wiegerinck W.A.J.J., Kappen H.J.
Risk sensitive path integral control.
UAI, vol. 26, pp. 1-8, 2010

Mejias FF., Kappen H.J., Torres J.J.
Irregular dynamics in up and down cortical states.
Plos One, vol. 5, no. 11, pp. 1-13, 2010

2009
G贸mez V., Kappen H.J., Chertkov, M
Approximate inference on planar graphs using loop calculus and belief propagation.
Proceedings UAI, vol. 25, pp. no pages, 2009

G贸mez V., Kaltenbrunner A., L脙鲁pez V., Kappen H.J.
Self-organization using synaptic plasticity.
Advances in Neural Information Processing Systems, vol. 22, pp. 513-520, 2009

Mooij J.M., Kappen H.J.
Bounds on marginal probability distributions.
Neural Information Processing Systems, vol. 22, pp. 1105-1113, 2009

Mooij J.M., Kappen H.J.
Novel bounds on marginal probabilities.
Journal for Machine Learning Research (JMLR), 2009

Llera A., G贸mez V., Kappen H.J.
Sparse matrix factorization for brain computer interfaces_.
Proceedings of ABCI workshop, vol. xx, no. xx, pp. xxx, 2009

Mejias FF., Torres J.J., Johnson S., Kappen H.J.
Switching dynamics of neural systems in the presence of multiplicative colored noise.
Bio-Inspired Systems: Computational and Ambient Intelligence, pp. 17-23, 2009

Janss L., Kappen H.J.
Bayesian construction of perceptrons to predict phenotypes from 584k snp data..
PASCAL Computational Statistics Workshop, pp. Presentation, 2009

Gheshlaghi Azar M., Kappen H.J.
Dynamic policy programming with kl-divergence minimization.
NIPS Workshop on Probabilistic Approaches for Stochastic Optimal Control and Robotics, 2009

2008
Broek J.L. van den, Wiegerinck W.A.J.J., Kappen H.J.
Graphical model inference in optimal control of stochastic multi-agent systems.
Journal of Artificial Intelligence Research, vol. 32, pp. 95-122, 2008

Broek J.L. van den, Wiegerinck W.A.J.J., Kappen H.J.
Optimal control in large stochastic multi-agent systems.
Adaptive Agents and Multi-Agent Systems III. Adaptation and Multi-Agent Learning, vol. 4865, pp. 15-26, 2008

Broek J.L. van den, Wiegerinck W.A.J.J., Kappen H.J.
Optimal control in large stochastic multi-agent systems.
Alamas 07, Maastricht 2-3 April., pp. 9-20, 2008

Albers C.A., Stankovich J., Thomson T., Bahlo M., Kappen H.J.
Multipoint approximations of identity-by-descent probabilities for accurate linkage analysis of distantly-related individuals.
American Journal of Human Genetics, vol. 82, no. web only, pp. 607-622, 2008

Welling M., Teh Y., Kappen H.J.
Hybrid variational / gibbs collapsed inference in topic models.
UAI, vol. Website Only, pp. 1-8, 2008

2007
Albers C.A., Kappen H.J.
Modeling linkage disequilibrium in exact linkage.
BMC Proceedings of the genetic Analysis Workshop 15: Gene Expression Analysis and Approaches to Detecting Multiple Functional, vol. 1, pp. S159, 2007

G贸mez V., Mooij J.M., Kappen H.J.
Truncating the loop series expansion for bp..
Journal for Machine Learning Research (JMLR), vol. 8, pp. 1987-2016, 2007

Wiegerinck W.A.J.J., Broek J.L. van den, Kappen H.J.
Optimal on-line scheduling in stochastic multi-agent systems in continuous space and time.
AAMAS'07, vol. website, pp. 1-8, 2007

Kappen H.J.
An introduction to stochastic control theory, path integrals and reinforcement learning..
In 9th Granada seminar on Computational Physics: Computational and Mathematical Modeling of Cooperative Behavior in Neural Systems., pp. 149-181, 2007

Torres J.J., Marro J., Cortes J.M., Kappen H.J.
Attractor neural networks with activity-dependent synapses: the role of synaptic facilitation..
Neurocomputing, vol. 70, no. 10-12, pp. 2022-2025, 2007

Rizzo T., Wemmenhove B., Kappen H.J.
Cavity approximation for graphical models.
Physical Review E, section Statistical physics, vol. Rev. E 76, no. 011102, pp. 9 pages, 2007

Wemmenhove B., Mooij J.M., Wiegerinck W.A.J.J., Leisink M.A.R., Kappen H.J., Neijt J.P.
Inference in the promedas medical expert system.
Proceedings of the 11th Conference on Artificial Intelligence in Medicine (AIME 07), vol. 4594, pp. 456-460, 2007

Marinazzo D., Kappen H.J., Gielen C.C.A.M.
Input-driven oscillations in networs with excitatory and inhibitory neurons with dynamic synapses.
Neural Computation, vol. 19, pp. 1739-1765, 2007

Mooij J.M., Wemmenhove B., Kappen H.J., Rizzo T.
Loop corrected belief propagation.
Proceedings AISTATS 2007, vol. Website, pp. 8 pages, 2007

Torres J.J., Cortes J.M., Marro J., Kappen H.J.
Competition between synaptic depression and facilitation in attractor neural networks.
Neural Computation, vol. 19, pp. 2739-2755, 2007

Mooij J.M., Kappen H.J.
Sufficient conditions for convergence of the sum-product algorithm.
IEEE Transactions on Information Theory, vol. 53, no. 12, pp. 4422-4437, 2007

Mooij J.M., Kappen H.J.
Loop corrections for approximate inference on factor graphs.
Journal of Machine Learning Research, vol. 8, pp. 1113-1143, 2007

Albers C.A., Kappen H.J.
Haplotype inference in general pedigrees using the cluster variation method.
Genetics, no. 177, pp. 1101-1116, 2007

2006
Cortes J.M., Torres J.J., Marro J., Garrido P.L., Kappen H.J.
Effects of fast presynaptic noise in attractor neural networks.
Neural Computation, vol. 18, pp. 614-633, 2006

Albers C.A., Leisink M.A.R., Kappen H.J.
The cluster variation method for efficient linkage analysis on extended pedigrees.
BMC Bioinformatics, Special issue on Machine Learning in Computational Biology, vol. 7(Suppl 1), pp. S1, 2006

Wemmenhove B., Kappen H.J.
Survey propagation at finite temperature: application to a sourlas code as a toy model.
J. Phys. A: Math. Gen., vol. 39, pp. 1265-1283, 2006

Cemgil A.T., Kappen H.J., Barber D.
A generative model for music transcription.
IEEE Transactions on Speech and Audio Processing, vol. 14, pp. 679-694, 2006

Mols B., Neijt J.P., Kappen H.J.
Computer stelt straks medische diagnose: zeg eens @.
Intermediair, pp. 51-53, 2006

Wiegerinck W.A.J.J., Broek J.L. van den, Kappen H.J.
Stochastic optimal control in continuous space-time multi-agent systems.
UAI, vol. 22 th, pp. 528-535, 2006

Kappen H.J., Mainzer K,
Op zoek naar de ziel.
Zelfdenkende pillen en andere technologie die ons leven zal veranderen, pp. 217-223, 2006

Torres J.J., Cortes J.M., Wemmenhove B., Marro J., Kappen H.J.
Neural automata: the effect of microdynamics on unstable solutions.
2006

2005
Mooij J.M., Kappen H.J.
Sufficient conditions for convergence of loopy belief propagation.
Uncertainty in Artificial Intelligence, pp. 396-403, 2005

Kappen H.J.
Intelligente machines.
Inaugurele rede, pp. 1-23, 2005

Mooij J.M., Kappen H.J.
Validity estimates for loopy belief propagation on binary real-world networks.
Advances in Neural Information Processing Systems 17, vol. 17, pp. 945-952, 2005

Cortes J.M., Garrido P.L., Kappen H.J., Marro J., Morrillas C, Navivad D
Algorithms for identification and categorization.
Proceedings of the AIP Conference, vol. 779, pp. 178-184, 2005

Kappen H.J.
A linear theory for control of non-linear stochastic systems.
Physical Review Letters, vol. 95, pp. 200201, 2005

Kappen H.J.
Path integrals and symmetry breaking for optimal control theory.
Journal of Statistical Mechanics: Theory and Experiment, pp. P11011, 2005

Mooij J.M., Kappen H.J.
On the properties of the bethe approximation and loopy belief propagation on binary networks.
Journal of Statistical Mechanics: Theory and Experiment, pp. P110-12, 2005

2004
Bakker B., Neijt J.P., Kappen H.J.
Improving cox survival analysis with a neural-bayesian approach.
Statistics in Medicine, pp. 2989-3012, 2004

2003
Heskes T.M., Albers C.A., Kappen H.J.
Approximate inference and constrained optimization..
In: Proceedings UAI-2003, pp. 313-320, 2003

Cemgil A.T., Barber D., Kappen H.J.
A dynamical bayesian network for tempo and polyphonic pitch tracking.
Proceedings of the International Conference on Artificial Neural Networks, pp. CD, 2003

Pantic L., Torres J.J., Kappen H.J.
Coincidence detection with dynamic synapses.
Network: Computation in Neural Systems, vol. 14, pp. 17-33, 2003

Albers C.A., Kappen H.J.
Application of cluster variation method to genetic linkage analysis.
Proceedings BNAIC, vol. 15, pp. 11-18, 2003

Torres J.J., Pantic L., Kappen H.J.
On the role of synaptic depression in the performance of attractor neural networks.
AIP Conference Proceedings 661, pp. 174-180, 2003

Cemgil A.T., Kappen H.J.
Monte carlo methods for tempo tracking and rhythm quantization.
Journal of Artificial Intelligence Research, vol. 18, pp. 45-81, 2003

Leisink M.A.R., Kappen H.J.
Bound propagation.
Journal of Artificial Intelligence Research, pp. 139-154, 2003

Cemgil A.T., Kappen H.J., Barber D.
A generative model based polyphonic music transcription.
In Proceedings IEEE WASPAA, Workshop on Applications of Signal Processing to Audio and Acoustics., 2003

2002
Kappen H.J., Neijt J.P.
Promedas, a probabilistic decision support system for medical diagnosis.
SNN - UMCU, 2002

Leisink M.A.R., Kappen H.J., Brunner H.G.
Linkage analysis: a bayesian approach.
ICANN 2002, LNCS 2415, pp. 595-600, 2002

Cemgil A.T., Kappen H.J.
Integrating tempo tracking and quantization using particle filtering.
Proceedings of 2002 International Computer Music Conference, Gothenburg/Sweden, pp. 419-422, 2002

Kappen H.J., Wiegerinck W.A.J.J., Braak E.W.M.T. ter
Decision support for medical diagnosis.
Dealing with the data flood. Mining data, text and multimedia, pp. 111-121, 2002

Bakker B., Kappen H.J.
Approximate algorithms for neural-bayesian approaches.
Theoretical Computer Science, vol. 287, no. 1, pp. 219-238, 2002

Leisink M.A.R., Kappen H.J.
Means, correlations and bounds.
In: Advances in Neural Information Processing Systems, 14, vol. 14-1, pp. 455-462, 2002

Cemgil A.T., Kappen H.J.
Tempo tracking and rhythm quantization by sequential monte carlo.
Advances in Neural Information Processing Systems 14, Part VIII Applications, vol. 14-2, pp. 1361-1368, 2002

Pantic L., Torres J.J., Kappen H.J., Gielen C.C.A.M.
Associative memory with dynamic synapses.
Neural Computation, vol. 14, pp. 2903-2923, 2002

Kappen H.J.
The cluster variation method for approximate reasoning in medical diagnosis.
Modelling Bio-Medical Signals, pp. 3-16, 2002

Kappen H.J., Wiegerinck W.A.J.J.
Novel iteration schemes for the cluster variation method.
Advances in Neural Information Processing Systems 14, vol. 14, pp. 415-422, 2002

Leisink M.A.R., Kappen H.J.
General lower bounds based on computer generated higher order expansions..
In: Proceedings Uncertainty in AI 2002, vol. 18, pp. 293-210, 2002

Torres J.J., Pantic L., Kappen H.J.
On the storage capacity of attractor neural networks with depressing synapses.
Physical Review E, vol. 66, pp. 061910, 2002

2001
Cemgil A.T., Kappen H.J.
Bayesian real-time adaptation for interactive performance systems.
Proceedings of 2001 International Computer Music Conference, Havana/Cuba, pp. 147-150, 2001

Kappen H.J., Wiegerinck W.A.J.J.
Second order approximations for probability models.
Advances in Neural Information Processing Systems 11, vol. 13, pp. 238-244, 2001

Kappen H.J., Wiegerinck W.A.J.J., Nijman M.J.
Bayesbuilder.
Software Support for Bayesian Analysis Systems Proceedings, pp. 11-13, 2001

Kappen H.J., Wiegerinck W.A.J.J.
Mean field theory for graphical models.
Advanced mean field theory, pp. 37-49, 2001

Cemgil A.T., Kappen H.J., Desain P., Honing H.
On tempo tracking: tempogram representation and kalman filtering.
Journal of New Music Research, vol. 29, pp. 259-273, 2001

Kappen H.J.
An introduction to stochastic neural networks.
In: Handbook of Biological Physics, Neuro-informatics and Neural Modelling, vol. 4, pp. 517-552, 2001

Leisink M.A.R., Kappen H.J.
A tighter bound for graphical models.
Neural Computation, vol. 13, no. 9, pp. 2149--2171, 2001

Kappen H.J.
A novel iteration scheme for the cluster variation method.
Neural Information Processing Systems, vol. 13, pp. 415-422, 2001

Kappen H.J., Gielen C.C.A.M., Wiegerinck W.A.J.J., Cemgil A.T., Nijman M.J.
Approximate reasoning: real world applications of graphical models.
Foundations of Real-World Intelligence, pp. 73-121, 2001

Cemgil A.T., Kappen H.J.
A dynamic belief network implementation for realtime music transcription.
Proceedings of the 13th Belgian-Dutch Conference on Artificial Intelligence, pp. 473-474, 2001

Torres J.J., Willems P.H.G.M., Kappen H.J., Koopman W.J.H.
Hysteresis and bistability in a realistic model for ip3-driven ca oscillations.
Europhysics Letters, vol. 55, no. 5, pp. 746-752, 2001

Torres J.J., Kappen H.J., Willems P.H.G.M., Koopman W.J.H.
Mathematical model for calcium oscillations in non-excitable cells.
Biophysical Journal, vol. 80, pp. 613A, part 2, 2001

2000
Leisink M.A.R., Kappen H.J.
Linear response for higher order boltzmann machines.
Neural Networks, vol. 13 - 3, no. 3, pp. 329-335, 2000

Kappen H.J.
Constructing modular architectures with boltzmann machines.
Prerational Intelligence: Adaptive Behavior and Intelligent Systems Without Symbols and Logic., vol. 2, pp. 157-164, 2000

Leisink M.A.R., Kappen H.J.
A tighter bound for graphical models.
In Neural Information Processing Systems, NIPS 2000, Denver, USA, vol. 13, pp. 266-272, 2000

Kappen H.J., Leisink M.A.R.
Kansrijke methoden voor kunstmatig leren en redeneren.
Ned tijdschrift voor Natuurkunde, vol. 66, pp. 14-19, 2000

Cemgil A.T., Desain P., Kappen H.J.
Rhythm quantization for transcription.
Computer Music Journal, vol. 24, no. 2, pp. 60-75, 2000

Wiegerinck W.A.J.J., Kappen H.J.
Approximations of bayesian networks through kl minimisation.
New Generation Computing, vol. 18, no. 2, pp. 167-175, 2000

Kappen H.J., Spanjers J.J.
Mean field theory for asymmetric neural networks.
Physical Review E, vol. 61, pp. 5658-5663, 2000

Wiegerinck W.A.J.J., Kappen H.J., Leisink M.A.R., Barber D., Stroeve S.
Variational methods for approximate reasoning in graphical models.
RWC'2000 symposium, Tokyo, Japan, pp. 265-270, 2000

Bakker B., Kappen H.J.
Survival analysis: a neural-bayesian approach.
Proceedings Artificial Neural Networks in Medicine and Biology, pp. 162-167, 2000

Cemgil A.T., Kappen H.J.
A graphical model for music transcription.
In Neural Information Processing System, NIPS 2000, Denver, USA, 2000

Wiegerinck W.A.J.J., Kappen H.J.
A bridge between mean field theory and exact inference in probabilistic graphical models.
2000

Kappen H.J., Wiegerinck W.A.J.J.
Stochastic dynamics with dominant self-coupling.
Presentation "Learning",, 2000

Heskes T.M., Kappen H.J.
An application of linear response learning.
Proceedings of the 12th Belgium-Netherlands Artificial Intelligence Conference, pp. 117-124, 2000

Cemgil A.T., Kappen H.J., Desain P., Honing H.
On tempo tracking: tempogram representation and kalman filtering.
Int Computer Music Conf., Berlin, Sept. 2000, pp. 352-355, 2000

Pantic L., Torres J.J., Kappen H.J.
Coincidence detection with dynamic synapses.
Abstract Workshop NIPS'00, vol. 13, pp. workshop, 2000

Pantic L., Torres J.J., Kappen H.J.
On the role of dynamical synapses in coincidence detection.
Proceedings of CNS'2000, Neurocomputing, vol. 38-40, pp. 285-291, 2000

Kappen H.J.
Predicting newspaper sales: jed system 'weathers' the tests.
Newspaper Techniques, 2000

Leisink M.A.R., Kappen H.J.
Learning higher order boltzmann machines using linear response.
Neural Networks, vol. 13, pp. 329--335, 2000

Akaho S., Kappen H.J.
Nonmonotonic generalization bias of gaussian mixture models.
Ned tijdschrift voor Natuurkunde, vol. 12, pp. 1411Ã聝¢ï¿½ï¿½1427, 2000

1999
Leisink M.A.R., Kappen H.J.
Validity of tap equations in neural network.
Proceedings International Conference on Artificial Neural Networks 9, vol. 2, pp. 425-431, 1999

Stroeve S., Kappen H.J., Gielen C.C.A.M.
Stimulus segmentation in a stochastic neural network with exogenous signals.
Proceedings International Conference on Artificial Neural Networks 9, vol. 2, pp. 732-737, 1999

Wiegerinck W.A.J.J., Kappen H.J., Nijman M.J., Braak E.W.M.T. ter, Burg W.J.P.P. ter, Ying-Lie O.
Approximate inference for medical diagnosis.
Pattern Recognition Letters, vol. 20, pp. 1231-1239, 1999

Kappen H.J., Leisink M.A.R.
On the validity of mean field theory for finite size boltzmann machines.
Proceedings Snowbird 99, Utah, USA, 1999

Kappen H.J., Wiegerinck W.A.J.J., Nijman M.J.
Promedas. a probabilistic medical diagnostic advisory system.
Presentatie project Promedas, 1999

Cemgil A.T., Desain P., Kappen H.J.
Rhythm quantization for transcription.
Proceedings of the AISB'99 Convention, pp. 140-146, 1999

Kappen H.J., Wiegerinck W.A.J.J., Nijman M.J., Braak E.W.M.T. ter, Burg W.J.P.P. ter, Ying-Lie O.
Promedas. a probabilistic medical diagnostic advisory system.
AIM'99, pp. 16, 1999

Kappen H.J.
Glauber machines.
Technical Report SNN, NIPS'99 rejected, 1999

Bakker B., Kappen H.J.
A variational approach to bayesian survival analysis.
Advances in Neural Information Processing Systems 11, 1999

Leisink M.A.R., Kappen H.J.
An application of linear response learning.
IJCNN'2000, 1999

1998
Kappen H.J., Gielen C.C.A.M., Wiegerinck W.A.J.J., Barber D., Laar P. van de
Probabilistic knowledge representation.
RWC'98, Tokyo, Japan, pp. 285-292, 1998

Leisink M.A.R., Kappen H.J.
Learning higher order boltzmann machines using linear response.
Artificial Neural Networks 8, vol. 2, pp. 511-517, 1998

Akaho S., Kappen H.J.
Nonmonotonic generalization bias of gaussian mixture models.
Neural Computation, 1998

Kappen H.J., Rodriquez F.B.
Boltzmann machine learning using mean field theory and linear response correction.
Advances in Neural Information Processing Systems 10, pp. 280-286, 1998

Kappen H.J., Nijman M.J., Moorsel T. van
Learning active vision.
Industrial Applications of Neural Networks, pp. 193-202, 1998

Kappen H.J., Groothof M.
Just enough delivery.
INMA Ideas Magazine, pp. 23, 1998

1997
Nijman M.J., Kappen H.J.
Symmetry breaking and training from incomplete data with radial basis boltzmann machines.
International Journal of Neural Systems A, vol. 8, pp. 301-316, 1997

Nijman M.J., Kappen H.J.
Efficient learning in sparsely connected boltzmann machines.
Proceedings RWC'97, pp. 406-409, 1997

Kappen H.J.
Stimulus dependent correlations in stochastic networks.
Physical Review E, vol. 55, pp. 5849-5858, 1997

Kappen H.J., Rodriquez F.B.
Efficient learning in boltzmann machines using linear response theory.
Neural Computation, vol. 10, pp. 1137-1156, 1997

Kappen H.J., Rodriquez F.B.
Mean field approach to learning in boltzmann machines.
Pattern Recognition in Practice V, vol. 18, no. 11-13, pp. 1317-1322, 1997

Wiegerinck W.A.J.J., Burg W.J.P.P. ter, Dam P.S. van, Ying-Lie O., Neijt J.P., Kappen H.J.
An advisory system for anaemia based on boltzmann machines.
5th Eurpean Congres on Intelligent Techniques and Soft Computing, vol. 1, pp. 364-368, 1997

Kappen H.J.
A polynomial time algorithm for boltzmann machine learning.
Workshop Cambridge, 1997

Kappen H.J., Mempen, Dijken A. van, Otten H.A.F.M.
Voorspelling van frisdrankverkoop.
1997

Wiegerinck W.A.J.J., Kappen H.J., Gielen C.C.A.M.
Making decisions with probability models.
1997

Kappen H.J., Gielen C.C.A.M.
Neural networks: best practice in europe.
Neural Networks: Best Practice in Europe, pp. 209, 1997

Kappen H.J., Rodriquez F.B.
Accelerated learning in boltzmann machines using mean field theory.
Artificial Neural Networks 7, pp. 301-306, 1997

Wiegerinck W.A.J.J., Burg W.J.P.P. ter, Dam P.S. van, Ying-Lie O., Neijt J.P., Kappen H.J.
Lab-test selection in diagnosis of anaemia.
Neural Networks: Best Practice in Europe, pp. 179-181, 1997

Wiegerinck W.A.J.J., Kappen H.J.
Practical confidence and prediction intervals for prediction tasks.
Neural Networks: Best Practice in Europe, pp. 128-135, 1997

Kappen H.J., Wiegerinck W.A.J.J., Morgan T., Harris T.J., Paillet G., Kopecz K.
Stimulation initiative for european neural applications (siena).
Neural Networks: Best Practice in Europe, pp. 1-8, 1997

1996
unknown author: 168, Kappen H.J.
Neural network analysis to predict outcome in patients with ovarian cancer.
Artificial Neural Networks 5, Session 1, pp. 433-436, 1996

Tax D.M.J., Kappen H.J.
Learning structure with many-take-all networks.
Artificial Neural Networks 6, pp. 95-101, 1996

Nijman M.J., Kappen H.J.
Efficient learning in sparsely connected boltzmann machines.
Artificial Neural Networks 6, pp. 41-46, 1996

Kappen H.J.
Classification with inquiry.
1996

unknown author: 192, Kappen H.J.
Active decision.
Neural Networks, 1996

Kappen H.J., Theeuwen M.M.H.J.
Weersafhankelijkheid losse verkoop van kranten en tijdschriften in badplaatsen.
1996

Nijman M.J., Kappen H.J.
Efficient learning in sparselyconnected boltzmann machines.
NIPS, 1996

Wiegerinck W.A.J.J., Kappen H.J.
Lab-test selection in diagnosis of anaemia.
Proceedings RWC, Japan, pp. 83-88, 1996

Kappen H.J., Dijken A. van, Otten H.A.F.M.
Voorspelling van verkoop en inzet van personeel.
1996

Nijman M.J., Kappen H.J.
Efficient estimation of the partition function of anisotropic spin systems.
Physical Review Letters, 1996

Kappen H.J., Verona P.
Dynamic feature linking in stochastic networks with short range interactions.
Artificial Neural Networks 6, pp. 101-106, 1996

Wiegerinck W.A.J.J., Kappen H.J.
Doorbraak neurale netwerken afhankelijk van standaardisatie.
Automatiserings Gids, vol. 30, pp. 17, 1996

Wiegerinck W.A.J.J., Kappen H.J.
Siena: stimulation initiative for european neural applications.
Proceedings EUFIT'96, pp. 280-281, 1996

Kappen H.J.
An overview of neural network applications.
Proceedings 6th International Congress for Cumputer Technology in Agriculture, pp. 75-79, 1996

Kappen H.J., Theeuwen M.M.H.J.
Using neural networks to predict consumer behaviour.
Proceedings EUFIT'96, pp. 2149-2150, 1996

1995
Kappen H.J.
Deterministic learning rules for boltzmann machines.
Neural Networks, vol. 8, pp. 537-548, 1995

unknown author: 183, Kappen H.J.
Confidence intervals for neural networks.
1995

Kappen H.J., Nijman M.J., Motomura Y.
Radial basis boltzmann machines and learning with missing values.
World Conference on Neural Network, vol. 1, pp. 72-75, 1995

Kappen H.J., Pastoors A.G.W., Gielen C.C.A.M.
Confidence intervals for neural networks.
Proceedings of the International Conference on Digital Signal Processing, vol. 1, pp. 396-401, 1995

Heskes T.M., Kappen H.J.
Self-organization and nonparametric regression.
Artificial Neural Networks 5, vol. 1, pp. 81-86, 1995

Nijman M.J., Kappen H.J.
Radial basis boltzmann machines and incomplete data.
1995

Kappen H.J., Nijman M.J.
Dynamic linking in stochastic networks.
Brain Processes, Theories and models. Proceedings W.S. McCullock: 25 years in memoriam., pp. 294-299, 1995

Kappen H.J., Gielen C.C.A.M., Krose B.J.A.
Active perception and cognition.
RWC'95, Tokyo, Japan, pp. 13-14, 1995

Linders D., Kappen H.J.
Stochastic resonance and multimodal firing patterns in single-neuron models.
Neural networks: artificial intelligence and industrial applications, pp. 63-66, 1995

Kappen H.J., Nijman M.J., Moorsel T. van
Learning active vision: industrial application processing systems,.
Artificial Neural Networks 5, Session 7, Robotics, pp. 193-202, 1995

Kappen H.J., Gielen C.C.A.M.
Neural networks: artificial intelligence and industrial applications.
Proceedings of the 3rd SNN symposium, 1995

Kappen H.J., Theeuwen M.M.H.J.
Neurale netwerken en voorspelling losse verkoop.
1995

unknown author: 183, Kappen H.J.
Automatisering van neurale netwerken; een direct-mailing applicatie.
1995

1994
Kappen H.J., Willems P.
Neural network analysis to predict treatment outcome in patients with gynaecological cancer.
1994

Kappen H.J., Willems P.
Using neural networks for survival prediction.
Proceedings Interregional Dutch-German Biometric Meeting, 1994

Kappen H.J., Neijt J.P.
Neural network analysis to predict treatment outcome in patients with gynaecological cancer.
1994

Kappen H.J.
Using boltzmann machines for probability estimation: a general framework for neural network learning.
Proceedings Pattern Recognition in Practice IV, pp. 299-312, 1994

Laar P. van de, Kappen H.J.
Boltzmann machines and the em algoritm.
1994

Nijman M.J., Kappen H.J.
Using boltzmann machines to fill in missing values.
1994

unknown author: 168, Gielen C.C.A.M., Daelemans W., Kappen H.J.
Voorspelling samenstelling vliegas m.b.v neurale netwerken en symbolische methodes.
1994

unknown author: 168, Gielen C.C.A.M., Kappen H.J., Daelemans W.
Korte termijn voorspelling van vliegas m.b.v. neurale netwerken en symbolsch inductie methodes.
1994

Kappen H.J.
Neurale netwerken voor toepassingen op grote databases.
1994

unknown author: 168, Kappen H.J., Neijt J.P.
Neural network analysis to predict treatment outcome in patients with gynaecological cancer.
1994

Gielen C.C.A.M., Kappen H.J.
Neurale netwerken en hun toepassingen.
Informatie en Informatiebeleid, winter, vol. 12, no. 4, pp. 75-81, 1994

1993
Heskes T.M., Kappen H.J.
On-line learning processes in artificial neural networks.
vol. 51, pp. 199-234, 1993

Kappen H.J., Neijt J.P.
Neural network analysis to predict treatment outcome.
Annuals of Oncology, vol. 4, pp. 31-34, 1993

Kappen H.J.
Using boltzmann machines as perceptrons.
IEEE Trans. Neural Networks, 1993

Wiegerinck W.A.J.J., Kappen H.J.
Optimizing the architecture of multi-layer perceptrons for one-dimensional classification.
Artificial Neural Networks 3, pp. 558-561, 1993

Kappen H.J.
Using boltzmann machines for probability estimation.
Artificial Neural Networks 3, pp. 521-526, 1993

Hal R. van, Kappen H.J., Neijt J.P.
Neural network analysis for prediction of treatment outcome in ovarian cancer.
EWOC-3, 1993

Opstal A.J. van, Kappen H.J.
Neural representation of saccadic eye movements in monkey superior colliculus.
Artificial Neural Networks 3, pp. 88-93, 1993

Heskes T.M., Kappen H.J.
Learning processes in neural networks.
1993

Kappen H.J.
Error potentials for self-organization.
International Conference on Neural Networks, San Francisco, vol. 3, pp. 1219-1223, 1993

Slijpen E.T.P., Kappen H.J.
Cooling schedules for learning in neural networks.
Physical Review E, vol. 47, pp. 4457-4464, 1993

Kappen H.J.
Neurale netwerken, fuzzy rules en artificiele intelligentie.
Klinische Fysica, vol. 1, pp. 13-16, 1993

Opstal A.J. van, Kappen H.J.
A two-dimensional model for spatial-temporal transformation of saccades in monkey superior colliculus.
Network, vol. 4, pp. 19-38, 1993

Gielen C.C.A.M., Kappen H.J.
Proceedings of the international confidence icann'93.
Artificial Neural Networks 3, 1993

1992
Slijpen E.T.P., Kappen H.J.
Learning in neural networks with local minima.
Physical Review A, vol. 46, pp. 5221-5231, 1992

Kappen H.J.
Learning parameter adjustment in neural networks.
Physical Review A, vol. 45, pp. 8885-8893, 1992

Kappen H.J.
Learning rules, stochastic processes, and local minima.
Artificial Neural Networks 2, vol. 1, pp. 71-78, 1992

Kappen H.J., Neijt J.P.
Neural network analysis for prediction of treatment outcome in ovarian cancer.
ASCO, 1992

Kappen H.J., Gielen C.C.A.M.
Proceedings symposium on neural networks.
Proceedings of 2nd SNN Conference on Neural Networks, vol. 2, 1992

1991
Heskes T.M., Kappen H.J.
Learning processes in neural networks.
Physical Review A, vol. 44, pp. 2718-2726, 1991

Kappen H.J., Gielen C.C.A.M.
Neural networks learning in a changing environment.
Artificial Neural Networks 1, vol. 1, pp. 15-20, 1991

Kappen H.J.
Een computersimulatie van hetbilocale correlator model.
1991

Opstal A.J. van, Kappen H.J.
Quantitative model for spatio-temporal transformation of oculomotor signals in monkey superior colliculus..
Eur. J. Neurosci. (Suppl), vol. 14, pp. 56, 1991

Kappen H.J.
Neural networks learning in achanging environment.
International Joint Conference on Neural Networks, Seattle, vol. 1, pp. 823-828, 1991

Kappen H.J.
Learning at a constant rate.
1991

Kappen H.J.
Neurale netwerken: verslag van een symposium.
Informatie, vol. 33, pp. 435-438, 1991

Gielen C.C.A.M., Kappen H.J.
Proceedings symposium on neural networks.
Proceedings of 1st SNN symposium, vol. 1, 1991

1990
Kappen H.J., Gielen C.C.A.M.
Neurocomputing research in thenetherlands.
Neurocomputing, vol. 2, pp. 35-38, 1990

G贸mez V., Kappen H.J.
Latent kullback leibler control for continuous-state systems using probabilistic graphical models.
Proceedings UAI, vol. 30,


Other

Spaans Taalinstituut Marta Bela