AbstractÐThis paper describes a Bayesian approach for modeling 3D scenes as a collection of approximately planar layers that are arbitrarily positioned and oriented in the scene. In contrast to much of the previous work on layer-based motion modeling, which computes layered descriptions of 2D image motion, our work leads to a 3D description of the scene. There are two contributions within the paper. The first is to formulate the prior assumptions about the layers and scene within a Bayesian decision making framework which is used to automatically determine the number of layers and the assignment of individual pixels to layers. The second is algorithmic. In order to achieve the optimization, a Bayesian version of RANSAC is developed with which to initialize the segmentation. Then, a generalized expectation maximization method is used to find the MAP solution. Index TermsÐLayer extraction, segmentation, stereo matching, motion estimation. 1

The problem of source separation is by its very nature an inductive inference problem. There is not enough information to deduce the solution, so one must use any available information to infer the most probable solution. We demonstrate that source separation problems are well-suited for the Bayesian approach which provides a natural and logically consistent method by which one can incorporate prior knowledge to estimate the most probable solution given that knowledge. We derive the Bell-Sejnowski ICA algorithm from first principles, i.e. Bayes ' Theorem and demonstrate how the Bayesian methodology makes explicit the underlying assumptions. We then further demonstrate the power of the Bayesian approach by deriving two separation algorithms that

to be published in the special issue of Computer & Chemistry

Deformable geometric models can be used in the context of Bayesian analysis to solve ill-posed tomographic reconstruction problems. The uncertainties associated with a Bayesian analysis may be assessed by generating a set of random samples from the posterior, which may be accomplished using a Markov-Chain Monte-Carlo (MCMC) technique. We demonstrate the combination of these techniques for a reconstruction of a two-dimensional object from two orthogonal noisy projections. The reconstructed object is modeled in terms of a deformable geometrically-defined boundary with a uniform interior density yielding a nonlinear reconstruction problem. We show how an MCMC sequence can be used to estimate uncertainties in the location of the edge of the reconstructed object.

Brute-force dense matching is usually not satisfactory because the same search range is used for the entire image, yielding potentially many false matches. In this paper, we propose a progressive scheme for stereo matching which uses two fundamental concepts: the disparity gradient limit principle and the least commitment strategy. The first states that the disparity should vary smoothly almost everywhere, and the disparity gradient should not exceed a certain limit. The second states that we should first select only the most reliable matches and therefore postpone unreliable decisions until enough confidence is accumulated. Our technique starts with a few reliable point matches obtained automatically via feature correspondence or through user input. New matches are progressively added during an iterative matching process. At each stage, the current reliable matches constrain the search range for their neighbors according to the disparity gradient limit, thereby reducing potential matching ambiguities of those neighbors. Only unambiguous matches are selected and added to the set of reliable matches in accordance with the least commitment strategy. In addition, a correlation match measure that allows rotation of the match template is used to provide a more robust estimate. The entire process is cast within a Bayesian inference framework. Experimental results illustrate the robustness of our proposed dense stereo matching approach.

The main purpose of this article is to argue the merits of ‘population thinking’ in gaining insight into linguistic and, in particular, syntactic change. Population-level thinking and modelling can shed new light on many issues in the study of language acquisition and language change, and leads directly to a precise and useful characterisation of E-language. Something which is lacking in current generative linguistics. Moreover, this way of thinking is fully compatible with the major insights of the latter, and integrates them into a framework in which language variation and change are inherent and inevitable, rather than peripheral and/or accidental, properties of language. I will argue that (E-)languages are best modelled as particular kinds of dynamical systems; namely, complex adaptive systems (where these terms are used in technical senses made precise below). The article both introduces some relevant ideas and techniques from modern evolutionary theory, and from the mathematical and computational study of dynamical systems, and also offers a critique and review of some recent work on syntactic change in this emerging framework, arguing that a useful population model needs to support overlapping generations of language users and learners and to allow quite detailed modelling of differing demographic scenarios. I utilise simple linguistic scenarios based on constituent order changes to illustrate the ideas and techniques clearly. I abstract away from the sociolinguistic detail of the actuation

visualization of the problem to model human speech. A large number of example sequences of observation vectors (shown connected as continuous trajectories) depending on a given sequence of class labels, with each class representing for example a phoneme (here the name Keiko with given durations). In this synthetic example, the one-dimensional target data would be represented poorly by a uni-modal Gaussian distribution with a constant variance (which corresponds to using the squared-error objective function), which would average the two separate branches, indicated by the fat lines as the mean and constant variance of the single Gaussian. Compare this figure with Figure 3.10, Figure 3.11 and Figure 3.12 to see a subsequent improvement of the model.

The authors identify 2 major types of statistical data from which semantic representations can be learned. These are denoted as experiential data and distributional data. Experiential data are derived by way of experience with the physical world and comprise the sensory-motor data obtained through sense receptors. Distributional data, by contrast, describe the statistical distribution of words across spoken and written language. The authors claim that experiential and distributional data represent distinct data types and that each is a nontrivial source of semantic information. Their theoretical proposal is that human semantic representations are derived from an optimal statistical combination of these 2 data types. Using a Bayesian probabilistic model, they demonstrate how word meanings can be learned by treating experiential and distributional data as a single joint distribution and learning the statistical structure that underlies it. The semantic representations that are learned in this manner are measurably more realistic—as verified by comparison to a set of human-based measures of semantic representation—than those available from either data type individually or from both sources independently. This is not a result of merely using quantitatively more data, but rather it is because experiential and distributional data are qualitatively distinct, yet intercorrelated, types of data. The semantic representations that are learned are based on statistical structures that exist both within and between the experiential and distributional data types.

Abstract not found

We argue that the traditional notion of trust as a relation among entities, while useful, becomes insufficient for emerging data-centric mobile ad hoc networks. In these systems, setting the data trust level equal to the trust level of the data- providing entity would ignore system salient features, rendering applications ineffective and systems inflexible. This would be even more so if their operation is ephemeral, i.e., characterized by short-lived associations in volatile environments. In this paper, we address this challenge by extending the traditional notion of trust to data-centric trust: trustworthiness attributed to node-reported data per se. We propose a framework for data-centric trust establishment: First, trust in each individual piece of data is computed; then multiple, related but possibly contradictory, data are combined; finally, their validity is inferred by a decision component based on one of several evidence evaluation techniques. We consider and evaluate an instantiation of our framework in vehicular networks as a case study. Our simulation results show that our scheme is highly resilient to attackers and converges stably to the correct decision.