Página 16 dos resultados de 2413 itens digitais encontrados em 0.009 segundos

Redes Bayesianas aplicadas à análise do risco de crédito.; Bayesian networks applied to the anilysis of credit risk.

Karcher, Cristiane
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 26/02/2009 Português
Relevância na Pesquisa
37.279807%
Modelos de Credit Scoring são utilizados para estimar a probabilidade de um cliente proponente ao crédito se tornar inadimplente, em determinado período, baseadas em suas informações pessoais e financeiras. Neste trabalho, a técnica proposta em Credit Scoring é Redes Bayesianas (RB) e seus resultados foram comparados aos da Regressão Logística. As RB avaliadas foram as Bayesian Network Classifiers, conhecidas como Classificadores Bayesianos, com seguintes tipos de estrutura: Naive Bayes, Tree Augmented Naive Bayes (TAN) e General Bayesian Network (GBN). As estruturas das RB foram obtidas por Aprendizado de Estrutura a partir de uma base de dados real. Os desempenhos dos modelos foram avaliados e comparados através das taxas de acerto obtidas da Matriz de Confusão, da estatística Kolmogorov-Smirnov e coeficiente Gini. As amostras de desenvolvimento e de validação foram obtidas por Cross-Validation com 10 partições. A análise dos modelos ajustados mostrou que as RB e a Regressão Logística apresentaram desempenho similar, em relação a estatística Kolmogorov- Smirnov e ao coeficiente Gini. O Classificador TAN foi escolhido como o melhor modelo, pois apresentou o melhor desempenho nas previsões dos clientes maus pagadores e permitiu uma análise dos efeitos de interação entre variáveis.; Credit Scoring Models are used to estimate the insolvency probability of a customer...

Python Environment for Bayesian Learning: Inferring the Structure of Bayesian Networks from Knowledge and Data

Shah, Abhik; Woolf, Peter
Fonte: PubMed Publicador: PubMed
Tipo: Artigo de Revista Científica
Publicado em 01/06/2009 Português
Relevância na Pesquisa
37.255088%
In this paper, we introduce pebl, a Python library and application for learning Bayesian network structure from data and prior knowledge that provides features unmatched by alternative software packages: the ability to use interventional data, flexible specification of structural priors, modeling with hidden variables and exploitation of parallel processing.

Stochastic comparisons and Bayesian inference in software reliability; Ordenaciones estocásticas e inferencia bayesiana en fiabilidad de software

Torrado Robles, Nuria
Fonte: Universidade Carlos III de Madrid Publicador: Universidade Carlos III de Madrid
Tipo: Tese de Doutorado Formato: application/pdf
Português
Relevância na Pesquisa
37.255088%
Within the last decade of the 20th century and the first few years of the 21st century, the demand for complex software systems has increased, and therefore, the reliability of software systems has become a major concern for our modern society. Software reliability is defined as the probability of failure free software operations for a specified period of time in a specified environment. Many current software reliability techniques and practices are detailed by Lyu and Pham. From a statistical point of view, the random variables that characterize software reliability are the epoch times in which a failure of software takes place or the times between failures. Most of the well known models for software reliability are centered around the interfailure times or the point processes that they generate. A software reliability model specifies the general form of the dependence of the failure process on the principal factors that affect it: fault introduction, fault removal, and the operational environment. The purpose of this thesis is threefold: (1) to study stochastic properties of times between failures relative to independent but not identically distributed random variables; (2) to investigate properties of the epoch times of nonhomogeneous pure birth processes as an extension of nonhomogeneous Poisson processes used in the literature in software reliability modelling and...

The Non-Bayesian Restless Multi-Armed Bandit: A Case of Near-Logarithmic Strict Regret

Dai, Wenhan; Gai, Yi; Krishnamachari, Bhaskar; Zhao, Qing
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 07/09/2011 Português
Relevância na Pesquisa
37.279807%
In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \geq 1$ arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to be PSPACE-hard in general. We consider in this work the even harder non-Bayesian RMAB, in which the parameters of the Markov chain are assumed to be unknown \emph{a priori}. We develop an original approach to this problem that is applicable when the corresponding Bayesian problem has the structure that, depending on the known parameter values, the optimal solution is one of a prescribed finite set of policies. In such settings, we propose to learn the optimal policy for the non-Bayesian RMAB by employing a suitable meta-policy which treats each policy from this finite set as an arm in a different non-Bayesian multi-armed bandit problem for which a single-arm selection policy is optimal. We demonstrate this approach by developing a novel sensing policy for opportunistic spectrum access over unknown dynamic channels. We prove that our policy achieves near-logarithmic regret (the difference in expected reward compared to a model-aware genie)...

Deriving a Stationary Dynamic Bayesian Network from a Logic Program with Recursive Loops

Shen, Y. D.; Yang, Q.; You, J. H.; Yuan, L. Y.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 27/06/2005 Português
Relevância na Pesquisa
37.279807%
Recursive loops in a logic program present a challenging problem to the PLP framework. On the one hand, they loop forever so that the PLP backward-chaining inferences would never stop. On the other hand, they generate cyclic influences, which are disallowed in Bayesian networks. Therefore, in existing PLP approaches logic programs with recursive loops are considered to be problematic and thus are excluded. In this paper, we propose an approach that makes use of recursive loops to build a stationary dynamic Bayesian network. Our work stems from an observation that recursive loops in a logic program imply a time sequence and thus can be used to model a stationary dynamic Bayesian network without using explicit time parameters. We introduce a Bayesian knowledge base with logic clauses of the form $A \leftarrow A_1,...,A_l, true, Context, Types$, which naturally represents the knowledge that the $A_i$s have direct influences on $A$ in the context $Context$ under the type constraints $Types$. We then use the well-founded model of a logic program to define the direct influence relation and apply SLG-resolution to compute the space of random variables together with their parental connections. We introduce a novel notion of influence clauses...

Learning Bayesian Nets that Perform Well

Greiner, Russell; Grove, Adam J.; Schuurmans, Dale
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 06/02/2013 Português
Relevância na Pesquisa
37.28901%
A Bayesian net (BN) is more than a succinct way to encode a probabilistic distribution; it also corresponds to a function used to answer queries. A BN can therefore be evaluated by the accuracy of the answers it returns. Many algorithms for learning BNs, however, attempt to optimize another criterion (usually likelihood, possibly augmented with a regularizing term), which is independent of the distribution of queries that are posed. This paper takes the "performance criteria" seriously, and considers the challenge of computing the BN whose performance - read "accuracy over the distribution of queries" - is optimal. We show that many aspects of this learning task are more difficult than the corresponding subtasks in the standard model.; Comment: Appears in Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence (UAI1997)

Bayesian Structure Learning for Markov Random Fields with a Spike and Slab Prior

Chen, Yutian; Welling, Max
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
37.28901%
In recent years a number of methods have been developed for automatically learning the (sparse) connectivity structure of Markov Random Fields. These methods are mostly based on L1-regularized optimization which has a number of disadvantages such as the inability to assess model uncertainty and expensive cross-validation to find the optimal regularization parameter. Moreover, the model's predictive performance may degrade dramatically with a suboptimal value of the regularization parameter (which is sometimes desirable to induce sparseness). We propose a fully Bayesian approach based on a "spike and slab" prior (similar to L0 regularization) that does not suffer from these shortcomings. We develop an approximate MCMC method combining Langevin dynamics and reversible jump MCMC to conduct inference in this model. Experiments show that the proposed model learns a good combination of the structure and parameter values without the need for separate hyper-parameter tuning. Moreover, the model's predictive performance is much more robust than L1-based methods with hyper-parameter settings that induce highly sparse model structures.; Comment: Accepted in the Conference on Uncertainty in Artificial Intelligence (UAI), 2012

Bayesian Structure Learning for Markov Random Fields with a Spike and Slab Prior

Chen, Yutian; Welling, Max
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 09/08/2014 Português
Relevância na Pesquisa
37.28901%
In recent years a number of methods have been developed for automatically learning the (sparse) connectivity structure of Markov Random Fields. These methods are mostly based on L1-regularized optimization which has a number of disadvantages such as the inability to assess model uncertainty and expensive crossvalidation to find the optimal regularization parameter. Moreover, the model's predictive performance may degrade dramatically with a suboptimal value of the regularization parameter (which is sometimes desirable to induce sparseness). We propose a fully Bayesian approach based on a "spike and slab" prior (similar to L0 regularization) that does not suffer from these shortcomings. We develop an approximate MCMC method combining Langevin dynamics and reversible jump MCMC to conduct inference in this model. Experiments show that the proposed model learns a good combination of the structure and parameter values without the need for separate hyper-parameter tuning. Moreover, the model's predictive performance is much more robust than L1-based methods with hyper-parameter settings that induce highly sparse model structures.; Comment: Appears in Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012)

Learning Bayesian Networks with the bnlearn R Package

Scutari, Marco
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
37.28901%
bnlearn is an R package which includes several algorithms for learning the structure of Bayesian networks with either discrete or continuous variables. Both constraint-based and score-based algorithms are implemented, and can use the functionality provided by the snow package to improve their performance via parallel computing. Several network scores and conditional independence algorithms are available for both the learning algorithms and independent use. Advanced plotting options are provided by the Rgraphviz package.; Comment: 22 pages, 4 pictures

Bayesian Sparse Tucker Models for Dimension Reduction and Tensor Completion

Zhao, Qibin; Zhang, Liqing; Cichocki, Andrzej
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 10/05/2015 Português
Relevância na Pesquisa
37.28901%
Tucker decomposition is the cornerstone of modern machine learning on tensorial data analysis, which have attracted considerable attention for multiway feature extraction, compressive sensing, and tensor completion. The most challenging problem is related to determination of model complexity (i.e., multilinear rank), especially when noise and missing data are present. In addition, existing methods cannot take into account uncertainty information of latent factors, resulting in low generalization performance. To address these issues, we present a class of probabilistic generative Tucker models for tensor decomposition and completion with structural sparsity over multilinear latent space. To exploit structural sparse modeling, we introduce two group sparsity inducing priors by hierarchial representation of Laplace and Student-t distributions, which facilitates fully posterior inference. For model learning, we derived variational Bayesian inferences over all model (hyper)parameters, and developed efficient and scalable algorithms based on multilinear operations. Our methods can automatically adapt model complexity and infer an optimal multilinear rank by the principle of maximum lower bound of model evidence. Experimental results and comparisons on synthetic...

Multi-agent Inverse Reinforcement Learning for Zero-sum Games

Lin, Xiaomin; Beling, Peter A.; Cogill, Randy
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
37.28901%
In this paper we introduce a Bayesian framework for solving a class of problems termed Multi-agent Inverse Reinforcement Learning (MIRL). Compared to the well-known Inverse Reinforcement Learning (IRL) problem, MIRL is formalized in the context of a stochastic game rather than a Markov decision process (MDP). Games bring two primary challenges: First, the concept of optimality, central to MDPs, loses its meaning and must be replaced with a more general solution concept, such as the Nash equilibrium. Second, the non-uniqueness of equilibria means that in MIRL, in addition to multiple reasonable solutions for a given inversion model, there may be multiple inversion models that are all equally sensible approaches to solving the problem. We establish a theoretical foundation for competitive two-agent MIRL problems and propose a Bayesian optimization algorithm to solve the problem. We focus on the case of two-person zero-sum stochastic games, developing a generative model for the likelihood of unknown rewards of agents given observed game play assuming that the two agents follow a minimax bipolicy. As a numerical illustration, we apply our method in the context of an abstract soccer game. For the soccer game, we investigate relationships between the extent of prior information and the quality of learned rewards. Results suggest that covariance structure is more important than mean value in reward priors.

The Non-Bayesian Restless Multi-Armed Bandit: a Case of Near-Logarithmic Regret

Dai, Wenhan; Gai, Yi; Krishnamachari, Bhaskar; Zhao, Qing
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 22/11/2010 Português
Relevância na Pesquisa
37.279807%
In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \geq 1$ arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to be PSPACE-hard in general. We consider in this work the even harder non-Bayesian RMAB, in which the parameters of the Markov chain are assumed to be unknown \emph{a priori}. We develop an original approach to this problem that is applicable when the corresponding Bayesian problem has the structure that, depending on the known parameter values, the optimal solution is one of a prescribed finite set of policies. In such settings, we propose to learn the optimal policy for the non-Bayesian RMAB by employing a suitable meta-policy which treats each policy from this finite set as an arm in a different non-Bayesian multi-armed bandit problem for which a single-arm selection policy is optimal. We demonstrate this approach by developing a novel sensing policy for opportunistic spectrum access over unknown dynamic channels. We prove that our policy achieves near-logarithmic regret (the difference in expected reward compared to a model-aware genie)...

Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling

Shang, Xiaocheng; Zhu, Zhanxing; Leimkuhler, Benedict; Storkey, Amos J.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 29/10/2015 Português
Relevância na Pesquisa
37.28901%
Monte Carlo sampling for Bayesian posterior inference is a common approach used in machine learning. The Markov Chain Monte Carlo procedures that are used are often discrete-time analogues of associated stochastic differential equations (SDEs). These SDEs are guaranteed to leave invariant the required posterior distribution. An area of current research addresses the computational benefits of stochastic gradient methods in this setting. Existing techniques rely on estimating the variance or covariance of the subsampling error, and typically assume constant variance. In this article, we propose a covariance-controlled adaptive Langevin thermostat that can effectively dissipate parameter-dependent noise while maintaining a desired target distribution. The proposed method achieves a substantial speedup over popular alternative schemes for large-scale machine learning applications.; Comment: Advances in Neural Information Processing Systems (NIPS), 2015

Near Optimal Bayesian Active Learning for Decision Making

Javdani, Shervin; Chen, Yuxin; Karbasi, Amin; Krause, Andreas; Bagnell, J. Andrew; Srinivasa, Siddhartha
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 24/02/2014 Português
Relevância na Pesquisa
37.28901%
How should we gather information to make effective decisions? We address Bayesian active learning and experimental design problems, where we sequentially select tests to reduce uncertainty about a set of hypotheses. Instead of minimizing uncertainty per se, we consider a set of overlapping decision regions of these hypotheses. Our goal is to drive uncertainty into a single decision region as quickly as possible. We identify necessary and sufficient conditions for correctly identifying a decision region that contains all hypotheses consistent with observations. We develop a novel Hyperedge Cutting (HEC) algorithm for this problem, and prove that is competitive with the intractable optimal policy. Our efficient implementation of the algorithm relies on computing subsets of the complete homogeneous symmetric polynomials. Finally, we demonstrate its effectiveness on two practical applications: approximate comparison-based learning and active localization using a robot manipulator.; Comment: Extended version of work appearing in the International conference on Artificial Intelligence and Statistics (AISTATS) 2014

Bayesian Sample Size Determination of Vibration Signals in Machine Learning Approach to Fault Diagnosis of Roller Bearings

Sahu, Siddhant; Sugumaran, V.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 25/02/2014 Português
Relevância na Pesquisa
37.28901%
Sample size determination for a data set is an important statistical process for analyzing the data to an optimum level of accuracy and using minimum computational work. The applications of this process are credible in every domain which deals with large data sets and high computational work. This study uses Bayesian analysis for determination of minimum sample size of vibration signals to be considered for fault diagnosis of a bearing using pre-defined parameters such as the inverse standard probability and the acceptable margin of error. Thus an analytical formula for sample size determination is introduced. The fault diagnosis of the bearing is done using a machine learning approach using an entropy-based J48 algorithm. The following method will help researchers involved in fault diagnosis to determine minimum sample size of data for analysis for a good statistical stability and precision.; Comment: 14 pages, 1 table, 6 figures

On Local Optima in Learning Bayesian Networks

Nielsen, Jens D.; Kocka, Tomas; Pena, Jose M.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 19/10/2012 Português
Relevância na Pesquisa
37.28901%
This paper proposes and evaluates the k-greedy equivalence search algorithm (KES) for learning Bayesian networks (BNs) from complete data. The main characteristic of KES is that it allows a trade-off between greediness and randomness, thus exploring different good local optima. When greediness is set at maximum, KES corresponds to the greedy equivalence search algorithm (GES). When greediness is kept at minimum, we prove that under mild assumptions KES asymptotically returns any inclusion optimal BN with nonzero probability. Experimental results for both synthetic and real data are reported showing that KES often finds a better local optima than GES. Moreover, we use KES to experimentally confirm that the number of different local optima is often huge.; Comment: Appears in Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence (UAI2003)

Scoring and Searching over Bayesian Networks with Causal and Associative Priors

Borboudakis, Giorgos; Tsamardinos, Ioannis
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
37.28901%
A significant theoretical advantage of search-and-score methods for learning Bayesian Networks is that they can accept informative prior beliefs for each possible network, thus complementing the data. In this paper, a method is presented for assigning priors based on beliefs on the presence or absence of certain paths in the true network. Such beliefs correspond to knowledge about the possible causal and associative relations between pairs of variables. This type of knowledge naturally arises from prior experimental and observational data, among others. In addition, a novel search-operator is proposed to take advantage of such prior knowledge. Experiments show that, using path beliefs improves the learning of the skeleton, as well as the edge directions in the network.; Comment: Accepted for publication to the 29th Conference on Uncertainty in Artificial Intelligence (UAI-2013). The content of the paper is identical to the published one, but the compiler at arXiv produces a 11 page long paper, whereas the compiler we used produces a 10 page long paper (page limit for the conference)

Learning Gaussian Networks

Geiger, Dan; Heckerman, David
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 27/02/2013 Português
Relevância na Pesquisa
37.28901%
We describe algorithms for learning Bayesian networks from a combination of user knowledge and statistical data. The algorithms have two components: a scoring metric and a search procedure. The scoring metric takes a network structure, statistical data, and a user's prior knowledge, and returns a score proportional to the posterior probability of the network structure given the data. The search procedure generates networks for evaluation by the scoring metric. Previous work has concentrated on metrics for domains containing only discrete variables, under the assumption that data represents a multinomial sample. In this paper, we extend this work, developing scoring metrics for domains containing all continuous variables or a mixture of discrete and continuous variables, under the assumption that continuous data is sampled from a multivariate normal distribution. Our work extends traditional statistical approaches for identifying vanishing regression coefficients in that we identify two important assumptions, called event equivalence and parameter modularity, that when combined allow the construction of prior distributions for multivariate normal parameters from a single prior Bayesian network specified by a user.; Comment: Appears in Proceedings of the Tenth Conference on Uncertainty in Artificial Intelligence (UAI1994)

Binary Classifier Calibration: Bayesian Non-Parametric Approach

Naeini, Mahdi Pakdaman; Cooper, Gregory F.; Hauskrecht, Milos
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 13/01/2014 Português
Relevância na Pesquisa
37.28901%
A set of probabilistic predictions is well calibrated if the events that are predicted to occur with probability p do in fact occur about p fraction of the time. Well calibrated predictions are particularly important when machine learning models are used in decision analysis. This paper presents two new non-parametric methods for calibrating outputs of binary classification models: a method based on the Bayes optimal selection and a method based on the Bayesian model averaging. The advantage of these methods is that they are independent of the algorithm used to learn a predictive model, and they can be applied in a post-processing step, after the model is learned. This makes them applicable to a wide variety of machine learning models and methods. These calibration methods, as well as other methods, are tested on a variety of datasets in terms of both discrimination and calibration performance. The results show the methods either outperform or are comparable in performance to the state-of-the-art calibration methods.

Using parameterized calculus questions for learning and assessment

Descalço, Luís; Carvalho, Paula Reis
Fonte: IEEE Publicador: IEEE
Tipo: Conferência ou Objeto de Conferência
Português
Relevância na Pesquisa
37.28901%
We have implemented a Web application reusing questions from two computer systems, true/false questions from Project A and multiple choice questions from Project B. Our application implements a Bayesian user model for diagnosing student knowledge in the topics covered. In this article we propose the use of this system for both learning and assessment in a calculus course, encouraging the students to work during the semester without increasing the work load for teachers.