Results 1  10
of
31
A Guide to the Literature on Learning Probabilistic Networks From Data
, 1996
"... This literature review discusses different methods under the general rubric of learning Bayesian networks from data, and includes some overlapping work on more general probabilistic networks. Connections are drawn between the statistical, neural network, and uncertainty communities, and between the ..."
Abstract

Cited by 193 (0 self)
 Add to MetaCart
This literature review discusses different methods under the general rubric of learning Bayesian networks from data, and includes some overlapping work on more general probabilistic networks. Connections are drawn between the statistical, neural network, and uncertainty communities, and between the different methodological communities, such as Bayesian, description length, and classical statistics. Basic concepts for learning and Bayesian networks are introduced and methods are then reviewed. Methods are discussed for learning parameters of a probabilistic network, for learning the structure, and for learning hidden variables. The presentation avoids formal definitions and theorems, as these are plentiful in the literature, and instead illustrates key concepts with simplified examples. Keywords Bayesian networks, graphical models, hidden variables, learning, learning structure, probabilistic networks, knowledge discovery. I. Introduction Probabilistic networks or probabilistic gra...
An Alternative Markov Property for Chain Graphs
 Scand. J. Statist
, 1996
"... Graphical Markov models use graphs, either undirected, directed, or mixed, to represent possible dependences among statistical variables. Applications of undirected graphs (UDGs) include models for spatial dependence and image analysis, while acyclic directed graphs (ADGs), which are especially conv ..."
Abstract

Cited by 71 (5 self)
 Add to MetaCart
Graphical Markov models use graphs, either undirected, directed, or mixed, to represent possible dependences among statistical variables. Applications of undirected graphs (UDGs) include models for spatial dependence and image analysis, while acyclic directed graphs (ADGs), which are especially convenient for statistical analysis, arise in such fields as genetics and psychometrics and as models for expert systems and Bayesian belief networks. Lauritzen, Wermuth, and Frydenberg (LWF) introduced a Markov property for chain graphs, which are mixed graphs that can be used to represent simultaneously both causal and associative dependencies and which include both UDGs and ADGs as special cases. In this paper an alternative Markov property (AMP) for chain graphs is introduced, which in some ways is a more direct extension of the ADG Markov property than is the LWF property for chain graph. 1 INTRODUCTION Graphical Markov models use graphs, either undirected, directed, or mixed, to represent...
Towards an integrated proteinprotein interaction network
 Research in Computational Molecular Biology, Proceedings 3500
, 2005
"... Protein–protein interactions play a major role in most cellular processes. Thus, the challenge of identifying the full repertoire of interacting proteins in the cell is of great importance and has been addressed both experimentally and computationally. Today, large scale experimental studies of prot ..."
Abstract

Cited by 35 (7 self)
 Add to MetaCart
(Show Context)
Protein–protein interactions play a major role in most cellular processes. Thus, the challenge of identifying the full repertoire of interacting proteins in the cell is of great importance and has been addressed both experimentally and computationally. Today, large scale experimental studies of protein interactions, while partial and noisy, allow us to characterize properties of interacting proteins and develop predictive algorithms. Most existing algorithms, however, ignore possible dependencies between interacting pairs and predict them independently of one another. In this study, we present a computational approach that overcomes this drawback by predicting protein–protein interactions simultaneously. In addition, our approach allows us to integrate various protein attributes and explicitly account for uncertainty of assay measurements. Using the language of relational Markov networks, we build a unified probabilistic model that includes all of these elements. We show how we can learn our model properties and then use it to predict all unobserved interactions simultaneously. Our results show that by modeling dependencies between interactions, as well as by taking into account protein attributes and measurement noise, we achieve a more accurate description of the protein interaction network. Furthermore, our approach allows us to gain new insights into the properties of interacting proteins. Key words: Markov networks, probabilistic graphical models, protein–protein interaction networks.
Sensorbased understanding of daily life via largescale use of common sense
 In Proc. AAAI06
, 2006
"... The use of large quantities of common sense has long been thought to be critical to the automated understanding of the world. To this end, various groups have collected repositories of common sense in machinereadable form. However, efforts to apply these large bodies of knowledge to enable correspon ..."
Abstract

Cited by 27 (2 self)
 Add to MetaCart
(Show Context)
The use of large quantities of common sense has long been thought to be critical to the automated understanding of the world. To this end, various groups have collected repositories of common sense in machinereadable form. However, efforts to apply these large bodies of knowledge to enable correspondingly largescale sensorbased understanding of the world have been few. Challenges have included semantic gaps between facts in the repositories and phenomena detected by sensors, fragility of reasoning in the face of noise, incompleteness of repositories, and slowness of reasoning with these large repositories. We show how to address these problems with a combination of novel sensors, probabilistic representation, webscale information retrieval and approximate reasoning. In particular, we show how to use the 50,000fact handentered OpenMind Indoor Common Sense database to interpret sensor traces of daytoday activities with 88 % accuracy (which is easy) and 32/53 % precision/recall (which is not).
Active and dynamic information fusion for multisensor systems with dynamic bayesian networks
 IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS, PART B,
, 2006
"... Many information fusion applications are often characterized by a high degree of complexity because: 1) data are often acquired from sensors of different modalities and with different degrees of uncertainty; 2) decisions must be made efficiently; and 3) the world situation evolves over time. To addr ..."
Abstract

Cited by 19 (2 self)
 Add to MetaCart
(Show Context)
Many information fusion applications are often characterized by a high degree of complexity because: 1) data are often acquired from sensors of different modalities and with different degrees of uncertainty; 2) decisions must be made efficiently; and 3) the world situation evolves over time. To address these issues, we propose an information fusion framework based on dynamic Bayesian networks to provide active, dynamic, purposive and sufficing information fusion in order to arrive at a reliable conclusion with reasonable time and limited resources. The proposed framework is suited to applications where the decision must be made efficiently from dynamically available information of diverse and disparate sources.
On Recovery Algorithm for Chain Graphs
, 1997
"... The class of chain graphs (CGs) involving both undirected graphs (= Markov networks) and directed acyclic graphs (= Bayesian networks) was introduced in middle eighties for description of probabilistic conditional independence structures. Every class of Markov equivalent CGs (that is CGs describing ..."
Abstract

Cited by 17 (3 self)
 Add to MetaCart
The class of chain graphs (CGs) involving both undirected graphs (= Markov networks) and directed acyclic graphs (= Bayesian networks) was introduced in middle eighties for description of probabilistic conditional independence structures. Every class of Markov equivalent CGs (that is CGs describing the same conditional independence structure) has a natural representative, which is called the largest CG. The paper presents socalled recovery algorithm, which on basis of the conditional independence structure given by a CG (in form of socalled dependency model) finds the largest CG, representing the corresponding class of Markov equivalent CGs. As a byproduct a graphical characterization of graphs, which are the largest CGs (for a class of Markov equivalent CGs) is obtained, and a simple algorithm changing every CG into the largest CG of the corresponding equivalence class is given. 1 INTRODUCTION Classic graphical approaches to description of probabilistic conditional independence stru...
Learning causally linked Markov random fields
 Proceedings of the 10th International Workshop on Artificial Intelligence and Statistics, January 6–8, 2005, Savannah Hotel, Barbados
, 2005
"... 1 Introduction Generative models are widely used within machinelearning. However, in many applications the graphical models involve exclusively causal, or exclusivelyundirected edges. In this paper we consider models that contain both types of edge, and suggest approximate learning methods for such ..."
Abstract

Cited by 16 (1 self)
 Add to MetaCart
1 Introduction Generative models are widely used within machinelearning. However, in many applications the graphical models involve exclusively causal, or exclusivelyundirected edges. In this paper we consider models that contain both types of edge, and suggest approximate learning methods for such models. The main contribution of this paper is the proposal of combiningvariational inference with the contrastive divergence algorithm to facilitate learning in systems involvingcausally linked Markov Random Fields (MRF's). We support our proposal with examples of learning in several domains. 2 Learning Causal Models One way to make generative models with stochastichidden variables is to use a directed acyclic graph as shown in Figure 1 (a). The difficulty in learning such&quot;causal &quot; models is that the posterior distribution over the hidden variables is intractable (except in certainspecial cases such as factor analysis, mixture models, square ICA or graphs that are very sparsely connected). Despite the intractability of the posterior, it is possible to optimize a bound on the log probability of the data by using a simple factorial distribution, Q(hx), as an approximation to the true posterior,
Cumulative distribution networks and the derivativesumproduct algorithm
"... We introduce a new type of graphical model called a ‘cumulative distribution network’ (CDN), which expresses a joint cumulative distribution as a product of local functions. Each local function can be viewed as providing evidence about possible orderings, or rankings, of variables. Interestingly, we ..."
Abstract

Cited by 16 (6 self)
 Add to MetaCart
(Show Context)
We introduce a new type of graphical model called a ‘cumulative distribution network’ (CDN), which expresses a joint cumulative distribution as a product of local functions. Each local function can be viewed as providing evidence about possible orderings, or rankings, of variables. Interestingly, we find that the conditional independence properties of CDNs are quite different from other graphical models. We also describe a messagepassing algorithm that efficiently computes conditional cumulative distributions. Due to the unique independence properties of the CDN, these messages do not in general have a onetoone correspondence with messages exchanged in standard algorithms, such as belief propagation. We demonstrate the application of CDNs for structured ranking learning using a previouslystudied multiplayer gaming dataset. 1
Separation An Completeness Properties For Amp Chain Graph Markov Models
 Ann. Statist
, 2000
"... This paper introduces ..."
A probabilistic methodology for integrating knowledge and experiments on biological networks
 J. Comput
, 2006
"... Biological systems are traditionally studied by focusing on a specific subsystem, building an intuitive model for it, and refining the model using results from carefully designed experiments. Modern experimental techniques provide massive data on the global behavior of biological systems, and system ..."
Abstract

Cited by 10 (1 self)
 Add to MetaCart
Biological systems are traditionally studied by focusing on a specific subsystem, building an intuitive model for it, and refining the model using results from carefully designed experiments. Modern experimental techniques provide massive data on the global behavior of biological systems, and systematically using these large datasets for refining existing knowledge is a major challenge. Here we introduce an extended computational framework that combines formalization of existing qualitative models, probabilistic modeling, and integration of highthroughput experimental data. Using our methods, it is possible to interpret genomewide measurements in the context of prior knowledge on the system, to assign statistical meaning to the accuracy of such knowledge, and to learn refined models with improved fit to the experiments. Our model is represented as a probabilistic factor graph, and the framework accommodates partial measurements of diverse biological elements. We study the performance of several probabilistic inference algorithms and show that hidden model variables can be reliably inferred even in the presence of feedback loops and complex logic. We show how to refine prior knowledge on combinatorial regulatory relations using hypothesis testing and derive pvalues for learned model features. We test our methodology and algorithms on a simulated model and on two real yeast models. In particular, we use our method to explore uncharacterized relations among regulators in the yeast response to hyperosmotic shock and in the yeast lysine biosynthesis system. Our integrative approach to the analysis of biological regulation is demonstrated to synergistically combine qualitative and quantitative evidence into concrete biological predictions. Key words: biological systems, probabilistic modeling, high throughput data. 1.