Results 1  10
of
20
Critical Remarks on Single Link Search in Learning Belief Networks
 In Proc. 12th Conf. on Uncertainty in Artificial Intelligence
, 1996
"... In learning belief networks, the single link lookahead search is widely adopted to reduce the search space. We show that there exists a class of probabilistic domain models which displays a special pattern of dependency. We analyze the behavior of several learning algorithms using different scoring ..."
Abstract

Cited by 28 (13 self)
 Add to MetaCart
In learning belief networks, the single link lookahead search is widely adopted to reduce the search space. We show that there exists a class of probabilistic domain models which displays a special pattern of dependency. We analyze the behavior of several learning algorithms using different scoring metrics such as the entropy, conditional independence, minimal description length and Bayesian metrics. We demonstrate that single link lookahead search procedures (employed in these algorithms) cannot learn these models correctly. Thus, when the underlying domain model actually belongs to this class, the use of a single link search procedure will result in learning of an incorrect model. This may lead to inference errors when the model is used. Our analysis suggests that if the prior knowledge about a domain does not rule out the possible existence of these models, a multilink lookahead search or other heuristics should be used for the learning process. 1 INTRODUCTION As many effective pr...
On the role of multiply sectioned Bayesian networks to cooperative multiagent systems
 IEEE Trans. Systems, Man, and CyberneticsPart A
"... Abstract—We consider a common task in multiagent systems where agents need to estimate the state of an uncertain domain so that they can act accordingly. If each agent only has partial knowledge about the domain and local observations, how can the agents accomplish the task with a limited amount of ..."
Abstract

Cited by 11 (4 self)
 Add to MetaCart
Abstract—We consider a common task in multiagent systems where agents need to estimate the state of an uncertain domain so that they can act accordingly. If each agent only has partial knowledge about the domain and local observations, how can the agents accomplish the task with a limited amount of communication? Multiply sectioned Bayesian networks (MSBNs) provide an effective and exact framework for such a task but also impose a set of constraints. Are there simpler frameworks with the same performance but with less constraints? We identify a small set of high level choices which logically imply the key representational choices leading to MSBNs. The result addresses the necessity of constraints of the framework. It facilitates comparisons with related frameworks and provides guidance to potential extensions of the framework. (Keywords: multiagent system, decentralized interpretation, communication, organization structure, uncertain reasoning, probabilistic reasoning, belief network, Bayesian network) I.
A Bayesian Approach to User Profiling In Information Retrieval
 TECHNOLOGY LETTERS
, 2000
"... Numerous probability models have been suggested for information retrieval (IR) over the years. These models have been applied to try to manage the inherent uncertainty in IR, for instance, document and query representation, relevance feedback, and evaluating the effectiveness of IR system. On ..."
Abstract

Cited by 9 (2 self)
 Add to MetaCart
Numerous probability models have been suggested for information retrieval (IR) over the years. These models have been applied to try to manage the inherent uncertainty in IR, for instance, document and query representation, relevance feedback, and evaluating the effectiveness of IR system. On the other hand, Bayesian networks have become an established probabilistic framework for uncertainty management in artificial intelligence. In this
Learning PseudoIndependent Models: Analytical and Experimental Results
 Advances in Artificial Intelligence
, 2000
"... . Most algorithms to learn belief networks use singlelink lookahead search to be efficient. It has been shown that such search procedures are problematic when applied to learning pseudoindependent (PI) models. Furthermore, some researchers have questioned whether PI models exist in practice. ..."
Abstract

Cited by 9 (5 self)
 Add to MetaCart
. Most algorithms to learn belief networks use singlelink lookahead search to be efficient. It has been shown that such search procedures are problematic when applied to learning pseudoindependent (PI) models. Furthermore, some researchers have questioned whether PI models exist in practice. We present two nontrivial PI models which derive from a social study dataset. For one of them, the learned PI model reached ultimate prediction accuracy achievable given the data only, while using slightly more inference time than the learned nonPI model. These models provide evidence that PI models are not simply mathematical constructs. To develop efficient algorithms to learn PI models effectively we benefit from studying and understanding such models in depth. We further analyze how multiple PI submodels may interact in a larger domain model. Using this result, we show that the RML algorithm for learning PI models can learn more complex PI models than previously known. Keywor...
Towards understanding of pseudoindependent domains
 In Poster Proc. 10th Inter. Symposium on Methodologies for Intelligent Systems
, 1997
"... A pseudoindependent (PI) domain is a problem domain where a proper subset of a set of collectively dependent variables displays marginal independence. Common algorithms for learning belief networks cannot learn a faithful representation of the domain dependence when the data is obtained from a PI d ..."
Abstract

Cited by 8 (8 self)
 Add to MetaCart
A pseudoindependent (PI) domain is a problem domain where a proper subset of a set of collectively dependent variables displays marginal independence. Common algorithms for learning belief networks cannot learn a faithful representation of the domain dependence when the data is obtained from a PI domain. Since we usually have no a priori knowledge whether a domain of interest is PI or not, we may learn an incorrect belief network, suffer from the consequence, and be not aware of it. Design of more reliable learning algorithms depends highly on a better understanding of these domains. This paper reports our progress towards such a goal. We characterize the whole spectrum of discrete PI domains with formal definitions. This forms a basis for studying them. We present our progress on parameterization of PI domains which eventually will lead to a better understanding of the mechanism that forms PI domains. Whether PI domains exist in practice is a common concern. We show that parity and modulus addition problems are special PI domains, which provides positive evidence. Application of our results to learning is discussed.
Automated Database Schema Design Using Mined Data Dependencies
 J. Amer. Soc. Inform. Sci
, 1998
"... Data dependencies are used in database schema design to enforce the correctness of a database as well as to reduce redundant data. These dependencies are usually determined from the semantics of the attributes and are then enforced upon the relations. This paper describes a bottomup procedure for d ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
Data dependencies are used in database schema design to enforce the correctness of a database as well as to reduce redundant data. These dependencies are usually determined from the semantics of the attributes and are then enforced upon the relations. This paper describes a bottomup procedure for discovering multivalued dependencies (MVDs) in observed data without knowing `a priori the relationships amongst the attributes. The proposed algorithm is an application of the technique we designed for learning conditional independencies in probabilistic reasoning. A prototype system for automated database schema design has been implemented. Experiments were carried out to demonstrate both the effectiveness and efficiency of our method. 1
A WellBehaved Algorithm for Simulating Dependence Structures of Bayesian Networks
 International Journal of Applied Mathematics
, 1999
"... Automatic generation of Bayesian network (BNs) structures (directed acyclic graphs) is an important step in experimental study of algorithms for inference in BNs and algorithms for learning BNs from data. Previously known simulation algorithms do not guarantee connectedness of generated structure ..."
Abstract

Cited by 6 (2 self)
 Add to MetaCart
Automatic generation of Bayesian network (BNs) structures (directed acyclic graphs) is an important step in experimental study of algorithms for inference in BNs and algorithms for learning BNs from data. Previously known simulation algorithms do not guarantee connectedness of generated structures or even successful genearation according to a user specification. We propose a simple, efficient and wellbehaved algorithm for automatic generation of BN structures. The performance of the algorithm is demonstrated experimentally. Keywords: directed acyclic graph, graph theory, simulation, Bayesian network. 1
Parallel Learning of Belief Networks in Large and Difficult Domains
 Paris (Department of Signal and Image Processing). She graduated from Ecole des Mines de Paris in 1986, received Ph.D from ENST Paris in 1990 and the Habilitation a Diriger des Recherches from University Paris 5 in
, 1999
"... Learning belief networks from large domains can be expensive even with singlelink lookahead search (SLLS). Since a SLLS cannot learn correctly in a class of problem domains, multilink lookahead search (MLLS) is needed which further increases the computational complexity. In our experiment, learnin ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
Learning belief networks from large domains can be expensive even with singlelink lookahead search (SLLS). Since a SLLS cannot learn correctly in a class of problem domains, multilink lookahead search (MLLS) is needed which further increases the computational complexity. In our experiment, learning in some difficult domains over more than a dozen variables took days. In this paper, we study how to use parallelism to speed up SLLS for learning in large domains and to tackle the increased complexity of MLLS for learning in difficult domains. We propose a natural decomposition of the learning task for parallel processing. We investigate two strategies for job allocation among processors to further improve load balancing and efficiency of the parallel system. For learning from very large datasets, we present a regrouping of the available processors such that slow data access through the file system can be replaced by fast memory access. Experimental results in a distributed memory MIMD c...
A Characterization of SingleLink Search in Learning Belief Networks
 Proc. Pacific Rim Knowledge Acquisition Workshop
, 1998
"... . One alternative to manual acquisition of belief networks from domain experts is automatic learning of these networks from data. Common algorithms for learning belief networks employ a singlelink lookahead search. It is unclear, however, what types of domain models are learnable by such algorithms ..."
Abstract

Cited by 4 (4 self)
 Add to MetaCart
. One alternative to manual acquisition of belief networks from domain experts is automatic learning of these networks from data. Common algorithms for learning belief networks employ a singlelink lookahead search. It is unclear, however, what types of domain models are learnable by such algorithms and what types of models will escape. We conjecture that these learning algorithms that use a singlelink search are specializations of a simple algorithm which we call LIM. We put forward arguments that support such a conjecture, and then provide an axiomatic characterization of models learnable by LIM. The characterization coupled with the conjecture identifies models that are definitely learnable and definitely unlearnable by a class of learning algorithms. It also identifies models that are highly likely to escape these algorithms. Research to formally prove the conjecture is ongoing. Keywords: knowledge acquisition, learning, knowledge discovery. 1 Introduction Belief networks [9, 5...
Convergence of Estimation of Distribution Algorithms for Finite Samples
"... Estimation of Distribution Algorithms (EDA) have been proposed as an extension of genetic algorithms. Our algorithm FDA assumes that the function to be optimized is additively decomposed (ADF). The interaction graph GADF is used to create exact or approximate factorizations of the Boltzmann distribu ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
Estimation of Distribution Algorithms (EDA) have been proposed as an extension of genetic algorithms. Our algorithm FDA assumes that the function to be optimized is additively decomposed (ADF). The interaction graph GADF is used to create exact or approximate factorizations of the Boltzmann distribution. Using Gibbs sampling instead of probabilistic logic sampling is investigated. We also discuss the algorithm LFDA which learns a Bayesian network from data. For both algorithms estimates of the necessary sample size N to find the optimum are derived. The bounds are based on statistical learning theory and PAC learning. If the assumptions of a factorization theorem are fulfilled, the upper bound of the sample size N of FDA is of order O(n ln n) where n is the size of the problem. The computational complexity per generation is O(N ∗ n). For LFDA a bound cannot be proven because the network learned might be far from optimal. In many applications the optimal network is not necessary for converge to the global optima. For the 2D Ising model only 60 % of the edges of GADF need to be contained in the learned graph. Bounds can be obtained for two new learning methods. The first one learns factor graphs instead of Bayesian networks, the second one detects the structure of the function by computing its Walsh or Fourier coefficients. The computational complexity to compute the Walsh coefficients is O(n 2 ln n). The networks computed by FDA and LFDA are analyzed for a set of benchmark functions.