Results 1  10
of
20
Inexact graph matching using learning and simulation of Bayesian networks. An empirical comparison between different approaches with synthetic data
, 2000
"... Estimation Distribution Algorithms (EDAs) is a quite recent topic in optimisation techniques. Several algorithms and approaches have already been proposed by different authors, but up to now there are very few papers showing their potential and comparing them to other evolutionary computation method ..."
Abstract

Cited by 7 (2 self)
 Add to MetaCart
Estimation Distribution Algorithms (EDAs) is a quite recent topic in optimisation techniques. Several algorithms and approaches have already been proposed by different authors, but up to now there are very few papers showing their potential and comparing them to other evolutionary computation methods and algorithms such as Genetic Algorithms (GAs). A problem such as inexact graph matching is NPhard and requires techniques that approximate to an acceptable solution. This problem arises when a non bijective correspondence is searched between two graphs G1 and G2 . A typical instance of this problem corresponds to the case where G1 is a model of the scene, and G2 is a graph derived from data (e.g. an image of the scene). EDA algorithms are well suited for this type of problems. This paper proposes to use EDA algorithms as a new approach for inexact graph matching. Also, two adaptations of the EDA approach to problems with constraints are described on the form of two techniques to cont...
Incremental Methods for Bayesian Network Learning
 Department de
, 1999
"... In this work we analyze the most relevant, in our opinion, algorithms for learning Bayesian Networks. We analyze methods that use goodnessoffit tests between tentative networks and data. Within this sort of learning algorithms we distinguish batch and incremental methods. Finally, we propose a sys ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
In this work we analyze the most relevant, in our opinion, algorithms for learning Bayesian Networks. We analyze methods that use goodnessoffit tests between tentative networks and data. Within this sort of learning algorithms we distinguish batch and incremental methods. Finally, we propose a system, called BANDOLER, that incrementally learns Bayesian Networks from data and prior knowledge. The incremental fashion of the system allows to modify the learning strategy and to introduce new prior knowledge during the learning process in the light of the already learnt structure. 1 Introduction The aim of this work is twofold. On the one hand, we introduce the state of the art on learning Bayesian networks. It is intended to be a tutorial on the learning methods based on goodnessoffit tests. We present the most significant, in our opinion, learning algorithms found in the literature, as well as the theory they are based on. On the other hand, we propose a research framework. The fiel...
An Exploration of Affect Factors and Their Role in User Technology Acceptance: Mediation and Causality
, 2006
"... Affect factors have gained researchers ’ attention in a number of fields. The Information Systems (IS) literature, however, shows some gaps and inconsistencies regarding the role of affect factors in human–computer interaction. Building upon prior research, this study aims at a better understanding ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
Affect factors have gained researchers ’ attention in a number of fields. The Information Systems (IS) literature, however, shows some gaps and inconsistencies regarding the role of affect factors in human–computer interaction. Building upon prior research, this study aims at a better understanding of affect factors by clarifying their relationships with each other and with other primary user acceptance factors. Two affect variables that are different in nature were examined: computer playfulness (CP) and perceived enjoyment (PE). We theoretically clarified and methodologically verified their mediating effects and causal relationships with other primary factors influencing user technology acceptance, namely perceived ease of use (PEOU), perceived usefulness (PU), and behavioral intention (BI). Quantitative data were analyzed using R.M. Baron and D. Kenny’s (1986) method for mediating effects and P.R. Cohen, A. Carlsson, L. Ballesteros, and R.S. Amant’s (1993) path analysis method for causal relationships.These analyses largely supported our hypotheses. Results from this research indicate that a PE→PEOU causal direction is favored, and PEOU partially mediates PE’s impacts on PU whereas PE fully mediates CP’s impact on PEOU. With the increased interest in various affect factors in user technology acceptance and use, our study sheds light on the role of affect factors from both theoretical and methodological perspectives. Practical implications are discussed as well. Along with unprecedented advances in information systems (IS), user technology acceptance research remains a focal topic. After decades of research, this area is considered by some researchers to be one of the most mature areas in
Java Grande Forum
, 2004
"... A la memòria de mon pare que m’inculcà que els llibres són una font immensa de coneixement A la meva mare que em revelà que els llibres són una font de plaer infinit To the memory of my father who inculcated in me that books are an immense source of knowledge To my mother who revealed me that books ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
(Show Context)
A la memòria de mon pare que m’inculcà que els llibres són una font immensa de coneixement A la meva mare que em revelà que els llibres són una font de plaer infinit To the memory of my father who inculcated in me that books are an immense source of knowledge To my mother who revealed me that books are a source of infinite pleasure Agraïments i Acknowledgments The first words will be to my parents, sister and brother... Les primeres paraules d’agraiment vull que siguin per la mare i el pare per tota la dedicació que van posar en la meva educació. S’hi van haver d’escarrassar molt per a que m’interesses la lectura i per motivarme en els estudis!!! Una forta abraçada a la meva germana i al meu germà amb qui tants jocs i baralles hem compartit. I would like to thank my advisor Ramon Sangüesa who introduced me in the field of
Refinement of Bayesian Network Structures upon New Data
"... Refinement of Bayesian network structures using new data becomes more and more relevant. Some work has been done there; however, one problem has not been considered yet what to do when new data has fewer or more attributes than the existing model. In both cases data contains important knowledge and ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Refinement of Bayesian network structures using new data becomes more and more relevant. Some work has been done there; however, one problem has not been considered yet what to do when new data has fewer or more attributes than the existing model. In both cases data contains important knowledge and every effort must be made in order to extract it. In this paper, we propose a general merging algorithm to deal with situations when new data has different set of attributes. The merging algorithm updates sufficient statistics when new data is received. It expands the flexibility of Bayesian network structure refinement methods. The new algorithm is evaluated in extensive experiments, and its applications are discussed at length. 1
The Bayesian Agent: an incremental approach for learning agents working under uncertainty
"... Abstract: Learning agents can benefit both from uncertainty representations and their associated inference methods. One of the representations that deal explicitly with uncertainty are Belief Networks, and specially Bayesian Belief networks. Updating beliefs and acquiring new knowledge can easil ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Abstract: Learning agents can benefit both from uncertainty representations and their associated inference methods. One of the representations that deal explicitly with uncertainty are Belief Networks, and specially Bayesian Belief networks. Updating beliefs and acquiring new knowledge can easily be performed in such networks. It seems natural that agents should be able to use them. Unfortunately, current methods for automatically learning Bayesian networks are mainly batch methods. This makes difficult their adaptation to the requirements of realtime agents. In this paper we present a modification of previous methods for learning Bayesian Networks that allows incremental learning. We also explore its use by learning agents. An example of application is given in the domain of web user tracking. Reference to formalisms other than probability are commented in order to allow agents to work in domains with a high level of imprecision and noise. 1
Tree Augmented Classification of Binary Data Minimizing Stochastic Complexity
, 2002
"... We establish the algorithms and procedures that augment by trees the classfiers of binary feature vectors in (Gyllenberg et. al. 1993, 1997, Gyllenberg et. al. 1999 and Gyllenberg and Koski 2002). The notion of augmenting a classifier by a tree is due to (Chow and Liu 1968) and in a more extensive f ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
We establish the algorithms and procedures that augment by trees the classfiers of binary feature vectors in (Gyllenberg et. al. 1993, 1997, Gyllenberg et. al. 1999 and Gyllenberg and Koski 2002). The notion of augmenting a classifier by a tree is due to (Chow and Liu 1968) and in a more extensive form due to (Friedman et. al. 1997). These techniques will in another report be primarily applied to unsupervised classification of bacterial DNA fingerprints (or electrophoretic patterns), c.f., (Gyllenberg and Koski 2001 (a), Rademaker et. al. 1999). By classification we mean here both the (unsupervised) procedures of finding the classes in (training) data of items as well as the actual outcome of the procedure, i.e., a partitioning of the items. By identification we mean the procedures for finding the assignment of items in classes, preestablished in one way or the other. The distinction should be clear, although the algorithms of classification as given in the sequel will also...
Article Learning Genetic Population Structures Using Minimization of Stochastic Complexity
"... entropy ..."
Towards Extracting Faithful and Descriptive Representations of Latent Variable Models
"... Methods that use latent representations of data, such as matrix and tensor factorization or deep neural methods, are becoming increasingly popular for applications such as knowledge base population and recommendation systems. These approaches have been shown to be very robust and scalable but, in co ..."
Abstract
 Add to MetaCart
Methods that use latent representations of data, such as matrix and tensor factorization or deep neural methods, are becoming increasingly popular for applications such as knowledge base population and recommendation systems. These approaches have been shown to be very robust and scalable but, in contrast to more symbolic approaches, lack interpretability. This makes debugging such models difficult, and might result in users not trusting the predictions of such systems. To overcome this issue we propose to extract an interpretable proxy model from a predictive latent variable model. We use a socalled pedagogical method, where we query our predictive model to obtain observations needed for learning a descriptive model. We describe two families of (presumably more) descriptive models, simple logic rules and Bayesian networks, and show how members of these families provide descriptive representations of matrix factorization models. Preliminary experiments on knowledge extraction from text indicate that even though Bayesian networks may be more faithful to a matrix factorization model than the logic rules, the latter are possibly more useful for interpretation and debugging. 1