A major inference task in Bayesian networks is explaining why some variables are observed in their particular states using a set of target variables. Existing methods for solving this problem often generate explanations that are either too simple (underspecified) or too complex (overspecified). In this paper, we introduce a method called Most Relevant Explanation (MRE) which finds a partial instantiation of the target variables that maximizes the generalized Bayes factor (GBF) as the best explanation for the given evidence. Our study shows that GBF has several theoretical properties that enable MRE to automatically identify the most relevant target variables in forming its explanation. In particular, conditional Bayes factor (CBF), defined as the GBF of a new explanation conditioned on an existing explanation, provides a soft measure on the degree of relevance of the variables in the new explanation in explaining the evidence given the existing explanation. As a result, MRE is able to automatically prune less relevant variables from its explanation. We also show that CBF is able to capture well the explaining-away phenomenon that is often represented in Bayesian networks. Moreover, we define two dominance relations between the candidate solutions and use the relations to generalize MRE to find a set of top explanations that is both diverse and representative. Case studies on several benchmark diagnostic Bayesian networks show that MRE is often able to find explanatory hypotheses that are not only precise but also concise.

This work considers the problem of learning the structure of multivariate linear tree models, which include a variety of directed tree graphical models with continuous, discrete, and mixed latent variables such as linear-Gaussian models, hidden Markov models, Gaussian mixture models, and Markov evolutionary trees. The setting is one where we only have samples from certain observed variables in the tree, and our goal is to estimate the tree structure (i.e., the graph of how the underlying hidden variables are connected to each other and to the observed variables). We propose the Spectral Recursive Grouping algorithm, an efficient and simple bottom-up procedure for recovering the tree structure from independent samples of the observed variables. Our finite sample size bounds for exact recovery of the tree structure reveal certain natural dependencies on underlying statistical and structural properties of the underlying joint distribution. Furthermore, our sample complexity guarantees have no explicit dependence on the dimensionality of the observed variables, making the algorithm applicable to many high-dimensional settings. At the heart of our algorithm is a spectral quartet test for determining the relative topology of a quartet of variables from second-order statistics.

This paper shows that maintaining logical consistency of an iris recognition system is a matter of finding a suitable partitioning of the input space in enrollable and unenrollable pairs by negotiating the user comfort and the safety of the biometric system. In other words, consistent enrollment is mandatory in order to preserve system consistency. A fuzzy 3-valued disambiguated model of iris recognition is proposed and analyzed in terms of completeness, consistency, user comfort and biometric safety. It is also shown here that the fuzzy 3-valued model of iris recognition is hosted by an 8-valued Boolean algebra of modulo 8 integers that represents the computational formalization in which a biometric system (a software agent) can achieve the artificial understanding of iris recognition in a logically consistent manner.

In mixtures-of-experts (ME) model, where a number of submodels (experts) are combined, there have been two longstanding problems: (i) how many experts should be chosen, given the size of the training data? (ii) given the total number of parameters, is it better to use a few very complex experts, or is it better to combine many simple experts? In this paper, we try to provide some insights to these problems through a theoretic study on a ME structure where $m$ experts are mixed, with each expert being related to a polynomial regression model of order $k$. We study the convergence rate of the maximum likelihood estimator (MLE), in terms of how fast the Kullback-Leibler divergence of the estimated density converges to the true density, when the sample size $n$ increases. The convergence rate is found to be dependent on both $m$ and $k$, and certain choices of $m$ and $k$ are found to produce optimal convergence rates. Therefore, these results shed light on the two aforementioned important problems: on how to choose $m$, and on how $m$ and $k$ should be compromised, for achieving good convergence rates.

With the exponential increase in the number of documents available online, e.g., news articles, weblogs, scientific documents, effective and efficient classification methods are required in order to deliver the appropriate information to specific users or groups. The performance of document classifiers critically depends, among other things, on the choice of the feature representation. The commonly used "bag of words" representation can result in a large number of features. Feature abstraction helps reduce a classifier input size by learning an abstraction hierarchy over the set of words. A cut through the hierarchy specifies a compressed model, where the nodes on the cut represent abstract features. In this paper, we compare feature abstraction with two other methods for dimensionality reduction, i.e., feature selection and Latent Dirichlet Allocation (LDA). Experimental results on two data sets of scientific publications show that classifiers trained using abstract features significantly outperform those trained using features that have the highest average mutual information with the class, and those trained using the topic distribution and topic words output by LDA. Furthermore, we propose an approach to automatic identification of a cut in order to trade off the complexity of classifiers against their performance. Our results demonstrate the feasibility of the proposed approach.

Desiderata for cognitive architectures that are to support the extent of human-level intelligence required in virtual humans imply the need to bridge a range of dichotomies faced by such architectures. The focus here is first on two general approaches to building such bridges — addition and reduction — and then on a pair of general tools – graphical models and piecewise continuous functions — that exploit the second approach towards developing such an architecture. Evaluation is in terms of the architecture’s demonstrated ability and future potential for bridging the dichotomies.

Web Effort Estimation is a process of predicting the efforts and cost in terms of money, schedule and staff for any software project system. Many estimation models have been proposed over the last three decades and it is believed that it is a must for the purpose of: Budgeting, risk analysis, project planning and control, and project improvement investment analysis. In this paper, we investigate the use of Fuzzy ID3 decision tree for software cost estimation; it is designed by integrating the principles of ID3 decision tree and the fuzzy set-theoretic concepts, enabling the model to handle uncertain and imprecise data when describing the software projects, which can improve greatly the accuracy of obtained estimates. MMRE and Pred are used as measures of prediction accuracy for this study. A series of experiments is reported using two different software projects datasets namely, Tukutuku and COCOMO'81 datasets. The results are compared with those produced by the crisp version of the ID3 decision tree.

It is widely recognized today that the management of imprecision and vagueness will yield more intelligent and realistic knowledge-based applications. Description Logics (DLs) are a family of knowledge representation languages that have gained considerable attention the last decade, mainly due to their decidability and the existence of empirically high performance of reasoning algorithms. In this paper, we extend the well known fuzzy ALC DL to the fuzzy SHIN DL, which extends the fuzzy ALC DL with transitive role axioms (S), inverse roles (I), role hierarchies (H) and number restrictions (N). We illustrate why transitive role axioms are difficult to handle in the presence of fuzzy interpretations and how to handle them properly. Then we extend these results by adding role hierarchies and finally number restrictions. The main contributions of the paper are the decidability proof of the fuzzy DL languages fuzzy-SI and fuzzy-SHIN, as well as decision procedures for the knowledge base satisfiability problem of the fuzzy-SI and fuzzy-SHIN.

Markov decision processes capture sequential decision making under uncertainty, where an agent must choose actions so as to optimize long term reward. The paper studies efficient reasoning mechanisms for Relational Markov Decision Processes (RMDP) where world states have an internal relational structure that can be naturally described in terms of objects and relations among them. Two contributions are presented. First, the paper develops First Order Decision Diagrams (FODD), a new compact representation for functions over relational structures, together with a set of operators to combine FODDs, and novel reduction techniques to keep the representation small. Second, the paper shows how FODDs can be used to develop solutions for RMDPs, where reasoning is performed at the abstract level and the resulting optimal policy is independent of domain size (number of objects) or instantiation. In particular, a variant of the value iteration algorithm is developed by using special operations over FODDs, and the algorithm is shown to converge to the optimal policy.

In a Bayesian learning setting, the posterior distribution of a predictive model arises from a trade-off between its prior distribution and the conditional likelihood of observed data. Such distribution functions usually rely on additional hyperparameters which need to be tuned in order to achieve optimum predictive performance; this operation can be efficiently performed in an Empirical Bayes fashion by maximizing the posterior marginal likelihood of the observed data. Since the score function of this optimization problem is in general characterized by the presence of local optima, it is necessary to resort to global optimization strategies, which require a large number of function evaluations. Given that the evaluation is usually computationally intensive and badly scaled with respect to the dataset size, the maximum number of observations that can be treated simultaneously is quite limited. In this paper, we consider the case of hyperparameter tuning in Gaussian process regression. A straightforward implementation of the posterior log-likelihood for this model requires O(N^3) operations for every iteration of the optimization procedure, where N is the number of examples in the input dataset. We derive a novel set of identities that allow, after an initial overhead of O(N^3), the evaluation of the score function, as well as the Jacobian and Hessian matrices, in O(N) operations. We prove how the proposed identities, that follow from the eigendecomposition of the kernel matrix, yield a reduction of several orders of magnitude in the computation time for the hyperparameter optimization problem. Notably, the proposed solution provides computational advantages even with respect to state of the art approximations that rely on sparse kernel matrices.