Linda C. Van Der Gaag (original) (raw)

Uploads

Papers by Linda C. Van Der Gaag

Research paper thumbnail of Probabilistic Graphical Models

Research paper thumbnail of Probability-based models for plausible reasoning

This thesis has been written while I was employed at the Centre for Mathematics and Computer Scie... more This thesis has been written while I was employed at the Centre for Mathematics and Computer Science. I like to thank the head of the Department of Software Technology, Jaco de Balcker, and the project leader of the Expert Systems Group, Peter Lucas, for letting me work on the subject of plausible reasoning all these years. Without the financial support and the freedom they have given me, the research reported would not have been possible. Furthermore, I am grateful to Jan Bergstra and Richard Gill for being my thesis supervisors; it was Richard Gill who pointed out to me the paper by Steffen Lauritzen and David Spiegelhalter that inspired the main ideas of this thesis. Most of all, however, I'd like to thank Steffen Lauritzen who invited me to Aalborg University in Denmark. My stay there has been extremely motivating and I have learned a great deal from him and Finn Verner Jensen. The many discussions we've had have turned out to be invaluable. Furthermore, I greatly appreciate Steffen Lauritzen's willingness to be a member of my reading committee. Then, I also want to thank the other members of the reading committee, Peter van Emde Boas, Paul Klint and Marc Bezem, who provided comments on an earlier draft of this thesis. I am particularly grateful to

Research paper thumbnail of Sensitivity Analysis in Gaussian Networks

Research paper thumbnail of Exploiting Stability for Compact Representation of Independency Models

Research paper thumbnail of Preserving precision as a guideline for interface design for mathematical models

Research paper thumbnail of Preprocessing the MAP Problem

Probabilistic Graphical Models, 2006

Research paper thumbnail of Monotonicity in Bayesian networks

Uncertainty in Artificial Intelligence, Jul 7, 2004

Research paper thumbnail of Probabilistic Graphical Models: 7th European Workshop, PGM 2014, Utrecht, The Netherlands, September 17-19, 2014. Proceedings

Springer eBooks, Aug 21, 2014

This book constitutes the refereed proceedings of the 7th International Workshop on Probabilistic... more This book constitutes the refereed proceedings of the 7th International Workshop on Probabilistic Graphical Models, PGM 2014, held in Utrecht, The Netherlands, in September 2014. The 38 revised full papers presented in this book were carefully reviewed and selected from 44 submissions. The papers cover all aspects of graphical models for probabilistic reasoning, decision making, and learning.

Research paper thumbnail of A cow-specific probability of having clinical mastitis for use in automatic milking systems

Research paper thumbnail of Bayesian Networks for Bio-monitoring

Research paper thumbnail of Towards uncertainty analysis of Bayesian networks

Research paper thumbnail of Compliance with the Hyperlipidaemia Consensus: Clinicians versus the Computer

Lecture Notes in Computer Science, 2003

... Page 5. 344 Wouter P. van Rijsinge et al. With these lipoprotein levels, these patients clear... more ... Page 5. 344 Wouter P. van Rijsinge et al. With these lipoprotein levels, these patients clearly were on the decision bound-ary of the consensus. ... CBO, Utrecht, 1998. 5. PCG Simons, A. Algra, MF van der Laak, DE Grobbee, and Y. van der Graaf (1999). ...

Research paper thumbnail of Naive Bayesian classifiers for the clinical diagnosis of classical swine fever

Naive Bayesian classifiers have been successfully applied for solving diagnostic problems in the ... more Naive Bayesian classifiers have been successfully applied for solving diagnostic problems in the medical domain, but are relatively new to the veterinary field. To demonstrate their potential, we constructed naive Bayesian classifiers for discriminating between Classical Swine Fever (CSF) infected and non-infected herds. To this end, we used data on 490 herds, collected during the 1997/1998 CSF epidemic in the Netherlands. A full naive Bayesian classifier and a selective one were constructed, and their classification accuracies were compared to that of a previously published diagnostic rule. The full classifier had a higher accuracy than the diagnostic rule; the selective classifier proved to be comparable to the rule. In contrast with the diagnostic rule, the two classifiers had the advantage of taking both the presence and the absence of clinical signs into account, which resulted in more discriminative power.

Research paper thumbnail of A Computational Architecture for N-Way Sensitivity Analysis of Bayesian Networks

Research paper thumbnail of Chapter 10. An Overview of Expert System Principles

Organization, Management, and Expert Systems, 1990

Research paper thumbnail of Proceedings of the 8th Dutch Conference on Artificial Intelligence

Research paper thumbnail of Visual Exploration of Uncertainty in

Research paper thumbnail of The Necessity of Bounded Treewidth for Efficient Inference in Bayesian Networks

Algorithms for probabilistic inference in Bayesian networks are known to have running times that ... more Algorithms for probabilistic inference in Bayesian networks are known to have running times that are worst-case exponential in the size of the network. For networks with a moralised graph of bounded treewidth, however, these algorithms take a time which is linear in the network's size. In this paper, we show that under the assumption of the Exponential Time Hypothesis (ETH), small treewidth of the moralised graph actually is a necessary condition for a Bayesian network to render inference efficient by an algorithm accepting arbitrary instances. We thus show that no algorithm can exist that performs inference on arbitrary Bayesian networks of unbounded treewidth in polynomial time, unless the ETH fails.

Research paper thumbnail of Learning Bayesian Network Parameters with Prior Knowledge about Context-Specific Qualitative Influences

Uncertainty in Artificial Intelligence, 2005

We present a method for learning the parame- ters of a Bayesian network with prior knowledge abou... more We present a method for learning the parame- ters of a Bayesian network with prior knowledge about the signs of influences between variables. Our method accommodates not just the standard signs, but provides for context-specific signs as well. We show how the various signs translate into order constraints on the network parameters and how isotonic regression can be used to

Research paper thumbnail of Compliance with the Hyperlipidaemia Consensus: Clinicians versus the Computer

Lecture Notes in Computer Science, 2003

... Page 5. 344 Wouter P. van Rijsinge et al. With these lipoprotein levels, these patients clear... more ... Page 5. 344 Wouter P. van Rijsinge et al. With these lipoprotein levels, these patients clearly were on the decision bound-ary of the consensus. ... CBO, Utrecht, 1998. 5. PCG Simons, A. Algra, MF van der Laak, DE Grobbee, and Y. van der Graaf (1999). ...

Research paper thumbnail of Probabilistic Graphical Models

Research paper thumbnail of Probability-based models for plausible reasoning

This thesis has been written while I was employed at the Centre for Mathematics and Computer Scie... more This thesis has been written while I was employed at the Centre for Mathematics and Computer Science. I like to thank the head of the Department of Software Technology, Jaco de Balcker, and the project leader of the Expert Systems Group, Peter Lucas, for letting me work on the subject of plausible reasoning all these years. Without the financial support and the freedom they have given me, the research reported would not have been possible. Furthermore, I am grateful to Jan Bergstra and Richard Gill for being my thesis supervisors; it was Richard Gill who pointed out to me the paper by Steffen Lauritzen and David Spiegelhalter that inspired the main ideas of this thesis. Most of all, however, I'd like to thank Steffen Lauritzen who invited me to Aalborg University in Denmark. My stay there has been extremely motivating and I have learned a great deal from him and Finn Verner Jensen. The many discussions we've had have turned out to be invaluable. Furthermore, I greatly appreciate Steffen Lauritzen's willingness to be a member of my reading committee. Then, I also want to thank the other members of the reading committee, Peter van Emde Boas, Paul Klint and Marc Bezem, who provided comments on an earlier draft of this thesis. I am particularly grateful to

Research paper thumbnail of Sensitivity Analysis in Gaussian Networks

Research paper thumbnail of Exploiting Stability for Compact Representation of Independency Models

Research paper thumbnail of Preserving precision as a guideline for interface design for mathematical models

Research paper thumbnail of Preprocessing the MAP Problem

Probabilistic Graphical Models, 2006

Research paper thumbnail of Monotonicity in Bayesian networks

Uncertainty in Artificial Intelligence, Jul 7, 2004

Research paper thumbnail of Probabilistic Graphical Models: 7th European Workshop, PGM 2014, Utrecht, The Netherlands, September 17-19, 2014. Proceedings

Springer eBooks, Aug 21, 2014

This book constitutes the refereed proceedings of the 7th International Workshop on Probabilistic... more This book constitutes the refereed proceedings of the 7th International Workshop on Probabilistic Graphical Models, PGM 2014, held in Utrecht, The Netherlands, in September 2014. The 38 revised full papers presented in this book were carefully reviewed and selected from 44 submissions. The papers cover all aspects of graphical models for probabilistic reasoning, decision making, and learning.

Research paper thumbnail of A cow-specific probability of having clinical mastitis for use in automatic milking systems

Research paper thumbnail of Bayesian Networks for Bio-monitoring

Research paper thumbnail of Towards uncertainty analysis of Bayesian networks

Research paper thumbnail of Compliance with the Hyperlipidaemia Consensus: Clinicians versus the Computer

Lecture Notes in Computer Science, 2003

... Page 5. 344 Wouter P. van Rijsinge et al. With these lipoprotein levels, these patients clear... more ... Page 5. 344 Wouter P. van Rijsinge et al. With these lipoprotein levels, these patients clearly were on the decision bound-ary of the consensus. ... CBO, Utrecht, 1998. 5. PCG Simons, A. Algra, MF van der Laak, DE Grobbee, and Y. van der Graaf (1999). ...

Research paper thumbnail of Naive Bayesian classifiers for the clinical diagnosis of classical swine fever

Naive Bayesian classifiers have been successfully applied for solving diagnostic problems in the ... more Naive Bayesian classifiers have been successfully applied for solving diagnostic problems in the medical domain, but are relatively new to the veterinary field. To demonstrate their potential, we constructed naive Bayesian classifiers for discriminating between Classical Swine Fever (CSF) infected and non-infected herds. To this end, we used data on 490 herds, collected during the 1997/1998 CSF epidemic in the Netherlands. A full naive Bayesian classifier and a selective one were constructed, and their classification accuracies were compared to that of a previously published diagnostic rule. The full classifier had a higher accuracy than the diagnostic rule; the selective classifier proved to be comparable to the rule. In contrast with the diagnostic rule, the two classifiers had the advantage of taking both the presence and the absence of clinical signs into account, which resulted in more discriminative power.

Research paper thumbnail of A Computational Architecture for N-Way Sensitivity Analysis of Bayesian Networks

Research paper thumbnail of Chapter 10. An Overview of Expert System Principles

Organization, Management, and Expert Systems, 1990

Research paper thumbnail of Proceedings of the 8th Dutch Conference on Artificial Intelligence

Research paper thumbnail of Visual Exploration of Uncertainty in

Research paper thumbnail of The Necessity of Bounded Treewidth for Efficient Inference in Bayesian Networks

Algorithms for probabilistic inference in Bayesian networks are known to have running times that ... more Algorithms for probabilistic inference in Bayesian networks are known to have running times that are worst-case exponential in the size of the network. For networks with a moralised graph of bounded treewidth, however, these algorithms take a time which is linear in the network's size. In this paper, we show that under the assumption of the Exponential Time Hypothesis (ETH), small treewidth of the moralised graph actually is a necessary condition for a Bayesian network to render inference efficient by an algorithm accepting arbitrary instances. We thus show that no algorithm can exist that performs inference on arbitrary Bayesian networks of unbounded treewidth in polynomial time, unless the ETH fails.

Research paper thumbnail of Learning Bayesian Network Parameters with Prior Knowledge about Context-Specific Qualitative Influences

Uncertainty in Artificial Intelligence, 2005

We present a method for learning the parame- ters of a Bayesian network with prior knowledge abou... more We present a method for learning the parame- ters of a Bayesian network with prior knowledge about the signs of influences between variables. Our method accommodates not just the standard signs, but provides for context-specific signs as well. We show how the various signs translate into order constraints on the network parameters and how isotonic regression can be used to

Research paper thumbnail of Compliance with the Hyperlipidaemia Consensus: Clinicians versus the Computer

Lecture Notes in Computer Science, 2003

... Page 5. 344 Wouter P. van Rijsinge et al. With these lipoprotein levels, these patients clear... more ... Page 5. 344 Wouter P. van Rijsinge et al. With these lipoprotein levels, these patients clearly were on the decision bound-ary of the consensus. ... CBO, Utrecht, 1998. 5. PCG Simons, A. Algra, MF van der Laak, DE Grobbee, and Y. van der Graaf (1999). ...