The Experts below are selected from a list of 5631 Experts worldwide ranked by ideXlab platform
Anders L. Madsen - One of the best experts on this subject based on the ideXlab platform.
-
on spi Lazy Evaluation of influence diagrams
Probabilistic Graphical Models, 2014Co-Authors: Rafael Cabanas, Andres Cano, Manuel Gomezolmedo, Anders L. MadsenAbstract:Influence Diagrams are an effective modelling framework for analysis of Bayesian decision making under uncertainty. Improving the performance of the Evaluation is an element of crucial importance as real-world decision problems are more and more complex. Lazy Evaluation is an algorithm used to evaluate Influence Diagrams based on message passing in a strong junction tree. This paper proposes the use of Symbolic Probabilistic Inference as an alternative to Variable Elimination for computing the clique-to-clique messages in Lazy Evaluation of Influence Diagrams.
-
Probabilistic Graphical Models - On SPI-Lazy Evaluation of Influence Diagrams
Probabilistic Graphical Models, 2014Co-Authors: Rafael Cabanas, Andres Cano, Manuel Gómez-olmedo, Anders L. MadsenAbstract:Influence Diagrams are an effective modelling framework for analysis of Bayesian decision making under uncertainty. Improving the performance of the Evaluation is an element of crucial importance as real-world decision problems are more and more complex. Lazy Evaluation is an algorithm used to evaluate Influence Diagrams based on message passing in a strong junction tree. This paper proposes the use of Symbolic Probabilistic Inference as an alternative to Variable Elimination for computing the clique-to-clique messages in Lazy Evaluation of Influence Diagrams.
-
approximate Lazy Evaluation of influence diagrams
15th Conference of the Spanish Association for Artificial Intelligence, 2013Co-Authors: Rafael Cabanas, Andres Cano, Manuel Gomezolmedo, Anders L. MadsenAbstract:Influence Diagrams are a tool used to represent and solve decision problems under uncertainty. One of the most efficient exact methods used to evaluate Influence Diagrams is Lazy Evaluation. This paper proposes the use of trees for representing potentials involved in an Influence Diagram in order to obtain an approximate Lazy Evaluation of decision problems. This method will allow to evaluate complex decision problems that are not evaluable with exact methods due to their computational cost. The experimental work compares the efficiency and goodness of the approximate solutions obtained using different kind of trees.
-
Lazy Evaluation of Symmetric Bayesian Decision Problems
arXiv: Artificial Intelligence, 2013Co-Authors: Anders L. Madsen, Finn Verner JensenAbstract:Solving symmetric Bayesian decision problems is a computationally intensive task to perform regardless of the algorithm used. In this paper we propose a method for improving the efficiency of algorithms for solving Bayesian decision problems. The method is based on the principle of Lazy Evaluation - a principle recently shown to improve the efficiency of inference in Bayesian networks. The basic idea is to maintain decompositions of potentials and to postpone computations for as long as possible. The efficiency improvements obtained with the Lazy Evaluation based method is emphasized through examples. Finally, the Lazy Evaluation based method is compared with the hugin and valuation-based systems architectures for solving symmetric Bayesian decision problems.
-
CAEPIA - Approximate Lazy Evaluation of Influence Diagrams
Advances in Artificial Intelligence, 2013Co-Authors: Rafael Cabanas, Andres Cano, Manuel Gómez-olmedo, Anders L. MadsenAbstract:Influence Diagrams are a tool used to represent and solve decision problems under uncertainty. One of the most efficient exact methods used to evaluate Influence Diagrams is Lazy Evaluation. This paper proposes the use of trees for representing potentials involved in an Influence Diagram in order to obtain an approximate Lazy Evaluation of decision problems. This method will allow to evaluate complex decision problems that are not evaluable with exact methods due to their computational cost. The experimental work compares the efficiency and goodness of the approximate solutions obtained using different kind of trees.
Finn Verner Jensen - One of the best experts on this subject based on the ideXlab platform.
-
Lazy Evaluation of Symmetric Bayesian Decision Problems
arXiv: Artificial Intelligence, 2013Co-Authors: Anders L. Madsen, Finn Verner JensenAbstract:Solving symmetric Bayesian decision problems is a computationally intensive task to perform regardless of the algorithm used. In this paper we propose a method for improving the efficiency of algorithms for solving Bayesian decision problems. The method is based on the principle of Lazy Evaluation - a principle recently shown to improve the efficiency of inference in Bayesian networks. The basic idea is to maintain decompositions of potentials and to postpone computations for as long as possible. The efficiency improvements obtained with the Lazy Evaluation based method is emphasized through examples. Finally, the Lazy Evaluation based method is compared with the hugin and valuation-based systems architectures for solving symmetric Bayesian decision problems.
-
Probabilistic Graphical Models - An extension of Lazy Evaluation for influence diagrams avoiding redundant variables in the potentials
2004Co-Authors: Marta Vomlelova, Finn Verner JensenAbstract:Standard methods for solving influence diagrams consist in stepwise elimination of variables, and along with elimination of a variable a set of new potentials over new domains is calculated. It is well known that these methods tend to produce unnecessarily large domains resulting in excessive consumption of time and memory. The Lazy Evaluation method represents only a partial solution to the problem. In this paper we extend any potential with two graphs over its domain representing the dependencies of variables. When a node A is eliminated, all necessary structural information for establishing the minimal sets of domains for potentials is contained in these graphs. We push Lazy Evaluation a step further to avoid performing unnecessary multiplications and subsequent division with equivalent potentials.
-
UAI - Lazy Evaluation of symmetric Bayesian decision problems
1999Co-Authors: Anders L. Madsen, Finn Verner JensenAbstract:Solving symmetric Bayesian decision problems is a computationally intensive task to perform regardless of the algorithm used. In this paper we propose a method for improving the efficiency of algorithms for solving Bayesian decision problems. The method is based on the principle of Lazy Evaluation - a principle recently shown to improve the efficiency of inference in Bayesian networks. The basic idea is to maintain decompositions of potentials and to postpone computations for as long as possible. The efficiency improvements obtained with the Lazy Evaluation based method is emphasized through examples. Finally, the Lazy Evaluation based method is compared with the HUGIN and valuation-based systems architectures for solving symmetric Bayesian decision problems.
H B Muhlhaus - One of the best experts on this subject based on the ideXlab platform.
-
on Lazy Evaluation as a tool to optimize the efficiency of large scale numerical simulations in python
International Conference on Conceptual Structures, 2010Co-Authors: Lutz Gross, Joel Fenwick, Artak Amirbekyan, Lin Gao, Arash Mohajeri, H B MuhlhausAbstract:Scientists working on mathematical models want to concentrate on the design of models. They pay little attention to numerical methods such as the finite element method (FEM), their implementation and parallelization. The escript module in python provides an environment in which scientists can define new models using a language of partial differential equation (PDE) and spatial functions which is natural for the formulation of continuous models. This approach defines a high level of abstraction from the underlying data structures and frees modelers from issues of optimized implementation and parallelization. In its current implementation escript evaluates expressions which define PDE coefficients immediately for all nodes or elements of an FEM mesh. In the paper we will demonstrate that for complex rheologies such as the Drucker-Prager plasticity model, the memory requirements for this strategy are the limiting factor for scaling up the mesh size. The python module is backed by an escript C++ library where the processing is performed. We will discuss an new extension to the PDE coefficient handling provided by this C++ library which uses a Lazy Evaluation technique and will demonstrate the efficiency of this new extension in terms of compute time and memory usage for a practical engineering application, namely the simulation of elastic-plastic, saturated porous media. (C) 2010 Published by Elsevier Ltd.
-
ICCS - On Lazy Evaluation as a tool to optimize the efficiency of large scale numerical simulations in Python
Procedia Computer Science, 2010Co-Authors: Lutz Gross, Joel Fenwick, Artak Amirbekyan, Lin Gao, Arash Mohajeri, H B MuhlhausAbstract:Scientists working on mathematical models want to concentrate on the design of models. They pay little attention to numerical methods such as the finite element method (FEM), their implementation and parallelization. The escript module in python provides an environment in which scientists can define new models using a language of partial differential equation (PDE) and spatial functions which is natural for the formulation of continuous models. This approach defines a high level of abstraction from the underlying data structures and frees modelers from issues of optimized implementation and parallelization. In its current implementation escript evaluates expressions which define PDE coefficients immediately for all nodes or elements of an FEM mesh. In the paper we will demonstrate that for complex rheologies such as the Drucker-Prager plasticity model, the memory requirements for this strategy are the limiting factor for scaling up the mesh size. The python module is backed by an escript C++ library where the processing is performed. We will discuss an new extension to the PDE coefficient handling provided by this C++ library which uses a Lazy Evaluation technique and will demonstrate the efficiency of this new extension in terms of compute time and memory usage for a practical engineering application, namely the simulation of elastic-plastic, saturated porous media. (C) 2010 Published by Elsevier Ltd.
Simon M Lucas - One of the best experts on this subject based on the ideXlab platform.
-
Lazy Evaluation for best first contextual handwriting recognition
International Conference on Document Analysis and Recognition, 1999Co-Authors: A C Downton, Simon M LucasAbstract:Lazy Evaluation is a best-first state space search method for contextual handwriting recognition which searches an ordered space and applies constraints at the earliest possible opportunity to maximise computational efficiency. Lazy Evaluation is well-suited to multi-level hypothesis verification because it operates recursively on a hierarchical semantic tree of context constraints. This paper describes the Lazy Evaluation algorithm in detail, and proves that, if ordered hypotheses for the lowest-level sub-patterns are provided as inputs, and the combined belief function is monotonic, then overall interpretations are guaranteed to be generated in best-first order. Applications of Lazy Evaluation to postcode dictionary and address recognition problems are outlined as illustrations of the algorithm.
-
ICDAR - Lazy Evaluation for best-first contextual handwriting recognition
Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318), 1999Co-Authors: A C Downton, Simon M LucasAbstract:Lazy Evaluation is a best-first state space search method for contextual handwriting recognition which searches an ordered space and applies constraints at the earliest possible opportunity to maximise computational efficiency. Lazy Evaluation is well-suited to multi-level hypothesis verification because it operates recursively on a hierarchical semantic tree of context constraints. This paper describes the Lazy Evaluation algorithm in detail, and proves that, if ordered hypotheses for the lowest-level sub-patterns are provided as inputs, and the combined belief function is monotonic, then overall interpretations are guaranteed to be generated in best-first order. Applications of Lazy Evaluation to postcode dictionary and address recognition problems are outlined as illustrations of the algorithm.
-
rapid best first retrieval from massive dictionaries by Lazy Evaluation of a syntactic neural network
International Conference on Networks, 1995Co-Authors: Simon M LucasAbstract:A new method of searching large dictionaries given uncertain inputs is described, based on the Lazy Evaluation of a syntactic neural network (SNN). The new method is shown to significantly outperform a conventional trie-based method for large dictionaries (e.g. in excess of 100,000 entries). Results are presented for the problem of recognising UK postcodes using dictionary sizes of up to 1 million entries. Most significantly, it is demonstrated that the SNN actually gets faster as more data is loaded into it.
-
ICNN - Rapid best-first retrieval from massive dictionaries by Lazy Evaluation of a syntactic neural network
Proceedings of ICNN'95 - International Conference on Neural Networks, 1Co-Authors: Simon M LucasAbstract:A new method of searching large dictionaries given uncertain inputs is described, based on the Lazy Evaluation of a syntactic neural network (SNN). The new method is shown to significantly outperform a conventional trie-based method for large dictionaries (e.g. in excess of 100,000 entries). Results are presented for the problem of recognising UK postcodes using dictionary sizes of up to 1 million entries. Most significantly, it is demonstrated that the SNN actually gets faster as more data is loaded into it.
Lutz Gross - One of the best experts on this subject based on the ideXlab platform.
-
on Lazy Evaluation as a tool to optimize the efficiency of large scale numerical simulations in python
International Conference on Conceptual Structures, 2010Co-Authors: Lutz Gross, Joel Fenwick, Artak Amirbekyan, Lin Gao, Arash Mohajeri, H B MuhlhausAbstract:Scientists working on mathematical models want to concentrate on the design of models. They pay little attention to numerical methods such as the finite element method (FEM), their implementation and parallelization. The escript module in python provides an environment in which scientists can define new models using a language of partial differential equation (PDE) and spatial functions which is natural for the formulation of continuous models. This approach defines a high level of abstraction from the underlying data structures and frees modelers from issues of optimized implementation and parallelization. In its current implementation escript evaluates expressions which define PDE coefficients immediately for all nodes or elements of an FEM mesh. In the paper we will demonstrate that for complex rheologies such as the Drucker-Prager plasticity model, the memory requirements for this strategy are the limiting factor for scaling up the mesh size. The python module is backed by an escript C++ library where the processing is performed. We will discuss an new extension to the PDE coefficient handling provided by this C++ library which uses a Lazy Evaluation technique and will demonstrate the efficiency of this new extension in terms of compute time and memory usage for a practical engineering application, namely the simulation of elastic-plastic, saturated porous media. (C) 2010 Published by Elsevier Ltd.
-
Lazy Evaluation of PDE coefficients in the EScript system
2010Co-Authors: Joel Fenwick, Lutz GrossAbstract:EScript is an extension to Python for solving partial differential equations on parallel computers. It is parallelised for both MPI and shared memory, multi-core systems using OpenMP. In this paper, we discuss Lazy Evaluation as a strategy to reduce the cost of evaluating the coefficients of PDEs prior to solving. We show that our implementation provides significant memory and time savings for a problem involving complex expressions.
-
ICCS - On Lazy Evaluation as a tool to optimize the efficiency of large scale numerical simulations in Python
Procedia Computer Science, 2010Co-Authors: Lutz Gross, Joel Fenwick, Artak Amirbekyan, Lin Gao, Arash Mohajeri, H B MuhlhausAbstract:Scientists working on mathematical models want to concentrate on the design of models. They pay little attention to numerical methods such as the finite element method (FEM), their implementation and parallelization. The escript module in python provides an environment in which scientists can define new models using a language of partial differential equation (PDE) and spatial functions which is natural for the formulation of continuous models. This approach defines a high level of abstraction from the underlying data structures and frees modelers from issues of optimized implementation and parallelization. In its current implementation escript evaluates expressions which define PDE coefficients immediately for all nodes or elements of an FEM mesh. In the paper we will demonstrate that for complex rheologies such as the Drucker-Prager plasticity model, the memory requirements for this strategy are the limiting factor for scaling up the mesh size. The python module is backed by an escript C++ library where the processing is performed. We will discuss an new extension to the PDE coefficient handling provided by this C++ library which uses a Lazy Evaluation technique and will demonstrate the efficiency of this new extension in terms of compute time and memory usage for a practical engineering application, namely the simulation of elastic-plastic, saturated porous media. (C) 2010 Published by Elsevier Ltd.