This paper proposes a method to construct an adaptive agent that is universal with respect to a given class of experts, where each expert is designed specifically for a particular environment. This adaptive control problem is formalized as the problem of minimizing the relative entropy of the adaptive agent from the expert that is most suitable for the unknown environment. If the agent is a passive observer, then the optimal solution is the well-known Bayesian predictor. However, if the agent is active, then its past actions need to be treated as causal interventions on the I/O stream rather than normal probability conditions. Here it is shown that the solution to this new variational problem is given by a stochastic controller called the Bayesian control rule, which implements adaptive behavior as a mixture of experts. Furthermore, it is shown that under mild assumptions, the Bayesian control rule converges to the control law of the most suitable expert.

We focus on credal nets, which are graphical models that generalise Bayesian nets to imprecise probability. We replace the notion of strong independence commonly used in credal nets with the weaker notion of epistemic irrelevance, which is arguably more suited for a behavioural theory of probability. Focusing on directed trees, we show how to combine the given local uncertainty models in the nodes of the graph into a global model, and we use this to construct and justify an exact message-passing algorithm that computes updated beliefs for a variable in the tree. The algorithm, which is linear in the number of nodes, is formulated entirely in terms of coherent lower previsions, and is shown to satisfy a number of rationality requirements. We supply examples of the algorithm's operation, and report an application to on-line character recognition that illustrates the advantages of our approach for prediction. We comment on the perspectives, opened by the availability, for the first time, of a truly efficient algorithm based on epistemic irrelevance.

Previously, it has been proven that for any undirected graph there exists a regular Gaussian distribution that is faithful to it (Lněnička & Matúš, 2007, Corollary 3). A stronger result has been proven for acyclic directed graphs: In certain measure-theoretic sense, almost all the regular Gaussian distributions that factorize with respect to an acyclic directed graph are faithful to it (Spirtes et al., 1993, Theorem 3.2). Therefore, this paper extends the latter result to chain graphs. It is worth mentioning that we have recently proved in (Peña, 2009) a result analogous to the one in this paper but for strictly positive discrete probability distributions with arbitrary prescribed sample space. It is also worth noticing that a result analogous to the one in this paper has been proven in (Levitz et al., 2001, Theorem 6.1) under the

Many problems of low-level computer vision and image processing, such as denoising, deconvolution, tomographic reconstruction or super-resolution, can be addressed by maximizing the posterior distribution of a sparse linear model (SLM). We show how higher-order Bayesian decision-making problems, such as optimizing image acquisition in magnetic resonance scanners, can be addressed by querying the SLM posterior covariance, unrelated to the density's mode. We propose a scalable algorithmic framework, with which SLM posteriors over full, high-resolution images can be approximated for the first time, solving a variational optimization problem which is convex iff posterior mode finding is convex. These methods successfully drive the optimization of sampling trajectories for real-world magnetic resonance imaging through Bayesian experimental design, which has not been attempted before. Our methodology provides new insight into similarities and differences between sparse reconstruction and approximate Bayesian inference, and has important implications for compressive sensing of real-world images.

When users rate objects, a sophisticated algorithm that takes into account ability or reputation may produce a fairer or more accurate aggregation of ratings than the straightforward arithmetic average. Recently a number of authors have proposed different co-determination algorithms where estimates of user and object reputation are refined iteratively together, permitting accurate measures of both to be derived directly from the rating data. However, simulations demonstrating these methods' efficacy assumed a continuum of rating values, consistent with typical physical modelling practice, whereas in most actual rating systems only a limited range of discrete values (such as a 5-star system) is employed. We perform a comparative test of several co-determination algorithms with different scales of discrete ratings and show that this seemingly minor modification in fact has a significant impact on algorithms' performance. Paradoxically, where rating resolution is low, increased noise in users' ratings may even improve the overall performance of the system.

The Logic Programming (LP) community, through the Association for Logic Programming (ALP) and its Executive Committee, decided to introduce for 2010 important changes in the way the main yearly results in LP and related areas are published. Whereas such results have appeared to date in standalone volumes of proceedings of the yearly International Conferences on Logic Programming (ICLP), and this method -fully in the tradition of Computer Science (CS)- has served the community well, it was felt that an effort needed to be made to achieve a higher level of compatibility with the publishing mechanisms of other fields outside CS. In order to achieve this goal without giving up the traditional CS conference format a different model has been adopted starting in 2010 in which the yearly ICLP call for submissions takes the form of a joint call for a) full papers to be considered for publication in a special issue of the journal, and b) shorter technical communications to be considered for publication in a separate, standalone volume, with both kinds of papers being presented by their authors at the conference. Together, the journal special issue and the volume of short technical communications constitute the proceedings of ICLP. This 26th International Conference on Logic Programming Special Issue is the first of a series of yearly special issues of Theory and Practice of Logic Programming (TPLP) putting this new model into practice.

World Wide Web (WWW) is the most popular global information sharing and communication system consisting of three standards .i.e., Uniform Resource Identifier (URL), Hypertext Transfer Protocol (HTTP) and Hypertext Mark-up Language (HTML). Information is provided in text, image, audio and video formats over the web by using HTML which is considered to be unconventional in defining and formalizing the meaning of the context...

Web development is a challenging research area for its creativity and complexity. The existing raised key challenge in web technology technologic development is the presentation of data in machine read and process able format to take advantage in knowledge based information extraction and maintenance [4]. Currently it is not possible to search and extract optimized results using full text queries because there is no such mechanism exists which can fully extract the semantic from full text queries and then look for particular knowledge based information. Mechanism of presenting information over the web in a format so that the humans as well as machines can understand the context leads to the concept of Semantic Web introduced by Tim Berners Lee [4]. Semantic web is a linked mesh of information to produce technologies capable of reasoning on semi structured information and processed by machines [4].

The four intensive problems to the software rose by the software industry .i.e., User System Communication / Human Machine Interface, Meta Data extraction, Information processing & management and Data representation are discussed in this research paper. To contribute in the field we have proposed and described an intelligent semantic oriented agent based search engine including the concepts of intelligent graphical user interface, natural language based information processing, data management and data reconstruction for the final user end information representation.

Magomedov I.A, Khazamov O.A department of Computer Science, Dagestan State Technical University, Makhachkala city, 367014 Abstract The approach of applying associative processor for decision making problem was proposed. It focuses on hardware implementations of fuzzy processing systems, associativity as effective management basis of fuzzy processor. The structural approach is being developed resulting in a quite simple and compact parallel associative memory unit (PAMU). The memory cost and speed comparison of processors with rigid and soft-variable structure is given. Also the example PAMU flashing is considered.