Useful ideas for exploiting time to engineer representations

Commentary on target article "From simple associations to systematic reasoning: a connectionist representation of rules, variables, and dynamic bindings using temporal synchrony", by L. Shastri and V. Ajjangadde, pp. 417-494

GTM: the generative topographic mapping

Latent variable models represent the probability density of data in a space of several dimensions in terms of a smaller number of latent, or hidden, variables. A familiar example is factor analysis which is based on a linear transformations between the latent space and the data space. In this paper we introduce a form of non-linear latent variable model called the Generative Topographic Mapping, for which the parameters of the model can be determined using the EM algorithm. GTM provides a principled alternative to the widely used Self-Organizing Map (SOM) of Kohonen (1982), and overcomes most of the significant limitations of the SOM. We demonstrate the performance of the GTM algorithm on a toy problem and on simulated data from flow diagnostics for a multi-phase oil pipeline.

Using generative models for handwritten digit recognition

We describe a method of recognizing handwritten digits by fitting generative models that are built from deformable B-splines with Gaussian ``ink generators'' spaced along the length of the spline. The splines are adjusted using a novel elastic matching procedure based on the Expectation Maximization (EM) algorithm that maximizes the likelihood of the model generating the data. This approach has many advantages. (1) After identifying the model most likely to have generated the data, the system not only produces a classification of the digit but also a rich description of the instantiation parameters which can yield information such as the writing style. (2) During the process of explaining the image, generative models can perform recognition driven segmentation. (3) The method involves a relatively small number of parameters and hence training is relatively easy and fast. (4) Unlike many other recognition schemes it does not rely on some form of pre-normalization of input images, but can handle arbitrary scalings, translations and a limited degree of image rotation. We have demonstrated our method of fitting models to images does not get trapped in poor local minima. The main disadvantage of the method is it requires much more computation than more standard OCR techniques.

GTM: the generative topographic mapping

Latent variable models represent the probability density of data in a space of several dimensions in terms of a smaller number of latent, or hidden, variables. A familiar example is factor analysis which is based on a linear transformations between the latent space and the data space. In this paper we introduce a form of non-linear latent variable model called the Generative Topographic Mapping, for which the parameters of the model can be determined using the EM algorithm. GTM provides a principled alternative to the widely used Self-Organizing Map (SOM) of Kohonen (1982), and overcomes most of the significant limitations of the SOM. We demonstrate the performance of the GTM algorithm on a toy problem and on simulated data from flow diagnostics for a multi-phase oil pipeline.

Developments of the generative topographic mapping

The generative topographic mapping (GTM) model was introduced by Bishop et al. (1998, Neural Comput. 10(1), 215-234) as a probabilistic re- formulation of the self-organizing map (SOM). It offers a number of advantages compared with the standard SOM, and has already been used in a variety of applications. In this paper we report on several extensions of the GTM, including an incremental version of the EM algorithm for estimating the model parameters, the use of local subspace models, extensions to mixed discrete and continuous data, semi-linear models which permit the use of high-dimensional manifolds whilst avoiding computational intractability, Bayesian inference applied to hyper-parameters, and an alternative framework for the GTM based on Gaussian processes. All of these developments directly exploit the probabilistic structure of the GTM, thereby allowing the underlying modelling assumptions to be made explicit. They also highlight the advantages of adopting a consistent probabilistic framework for the formulation of pattern recognition algorithms.

GTM: the generative topographic mapping

This thesis describes the Generative Topographic Mapping (GTM) --- a non-linear latent variable model, intended for modelling continuous, intrinsically low-dimensional probability distributions, embedded in high-dimensional spaces. It can be seen as a non-linear form of principal component analysis or factor analysis. It also provides a principled alternative to the self-organizing map --- a widely established neural network model for unsupervised learning --- resolving many of its associated theoretical problems. An important, potential application of the GTM is visualization of high-dimensional data. Since the GTM is non-linear, the relationship between data and its visual representation may be far from trivial, but a better understanding of this relationship can be gained by computing the so-called magnification factor. In essence, the magnification factor relates the distances between data points, as they appear when visualized, to the actual distances between those data points. There are two principal limitations of the basic GTM model. The computational effort required will grow exponentially with the intrinsic dimensionality of the density model. However, if the intended application is visualization, this will typically not be a problem. The other limitation is the inherent structure of the GTM, which makes it most suitable for modelling moderately curved probability distributions of approximately rectangular shape. When the target distribution is very different to that, theaim of maintaining an `interpretable' structure, suitable for visualizing data, may come in conflict with the aim of providing a good density model. The fact that the GTM is a probabilistic model means that results from probability theory and statistics can be used to address problems such as model complexity. Furthermore, this framework provides solid ground for extending the GTM to wider contexts than that of this thesis.

A generative probabilistic oriented wavelet model for texture segmentation

This Letter addresses image segmentation via a generative model approach. A Bayesian network (BNT) in the space of dyadic wavelet transform coefficients is introduced to model texture images. The model is similar to a Hidden Markov model (HMM), but with non-stationary transitive conditional probability distributions. It is composed of discrete hidden variables and observable Gaussian outputs for wavelet coefficients. In particular, the Gabor wavelet transform is considered. The introduced model is compared with the simplest joint Gaussian probabilistic model for Gabor wavelet coefficients for several textures from the Brodatz album [1]. The comparison is based on cross-validation and includes probabilistic model ensembles instead of single models. In addition, the robustness of the models to cope with additive Gaussian noise is investigated. We further study the feasibility of the introduced generative model for image segmentation in the novelty detection framework [2]. Two examples are considered: (i) sea surface pollution detection from intensity images and (ii) image segmentation of the still images with varying illumination across the scene.

A generative model for separating illumination and reflectance from images

It is well known that even slight changes in nonuniform illumination lead to a large image variability and are crucial for many visual tasks. This paper presents a new ICA related probabilistic model where the number of sources exceeds the number of sensors to perform an image segmentation and illumination removal, simultaneously. We model illumination and reflectance in log space by a generalized autoregressive process and Hidden Gaussian Markov random field, respectively. The model ability to deal with segmentation of illuminated images is compared with a Canny edge detector and homomorphic filtering. We apply the model to two problems: synthetic image segmentation and sea surface pollution detection from intensity images.

Inscribing the organization:representations in dispute between accounting and production

This paper assumes that a primary function of management accounting is the representation of "accounting facts" for purposes such as organizational control. Accountants are able to offer conventional techniques of control, such as standard costing, as a consequence of their ability to deploy accounting representations within managerial and economic models of organizational processes. Accounting competes, at times, with other 'professional' groups, such as production planning or quality management people, in this role of representing the organization to management. The paper develops its arguments around a case illustration of cost accounting set in a low technology manufacturing environment. The research relates to a case organization in which accountants are attempting to establish the reliability of accounting inscriptions of a simple manufacturing process. The case research focuses on the documents, the inscriptions that vie for managements' attention. It is these sometimes messy and inaccurate representations which enable control of complex and heterogeneous activities at a distance. At the end of our site visits we observe quality management systems in the ascendancy over the accountants' standard costing systems. © 2006 Elsevier Ltd. All rights reserved.

Regional representations in the EU:between diplomacy and interest mediation

What are regional representations in the European Union? What do they hope to achieve? Since the mid-1980s, sub-state actors in the EU such as county councils, Länder, Autonomous Communities, local, municipal and city authorities have been opening representative offices in Brussels – mini 'embassies' for their territories. Although on the surface these representations might look the same, in practice they operate according to very different dynamics. Whilst some rival national governments for a stake in EU policy development, others have more modest ambitions. This book offers a comprehensive assessment of the burgeoning phenomenon of regional representation in the EU. Considering evidence from old member states as well as those which joined the EU more recently, it looks at where strategies and aims differ, positioning various 'types' of representation closer to the work of embassies or to that carried out by lobbying groups. The author also considers how regional representations contribute to our understanding of multi-level governance in the EU.

Constructing localized non-linear projection manifolds in a principled way:hierarchical generative topographic mapping

It has been argued that a single two-dimensional visualization plot may not be sufficient to capture all of the interesting aspects of complex data sets, and therefore a hierarchical visualization system is desirable. In this paper we extend an existing locally linear hierarchical visualization system PhiVis (Bishop98a) in several directions: 1. We allow for em non-linear projection manifolds. The basic building block is the Generative Topographic Mapping. 2. We introduce a general formulation of hierarchical probabilistic models consisting of local probabilistic models organized in a hierarchical tree. General training equations are derived, regardless of the position of the model in the tree. 3. Using tools from differential geometry we derive expressions for local directionalcurvatures of the projection manifold. Like PhiVis, our system is statistically principled and is built interactively in a top-down fashion using the EM algorithm. It enables the user to interactively highlight those data in the parent visualization plot which are captured by a child model.We also incorporate into our system a hierarchical, locally selective representation of magnification factors and directional curvatures of the projection manifolds. Such information is important for further refinement of the hierarchical visualization plot, as well as for controlling the amount of regularization imposed on the local models. We demonstrate the principle of the approach on a toy data set andapply our system to two more complex 12- and 19-dimensional data sets.

Etude theorique et empirique des pratiques et des representations du loisir chez les meres de famille en France

L'objectif de cette thèse consiste à faire une analyse approfondie des méanismes d'articulation dialectique qui lient la sphère sociale du loisir aux sphères de la production éonomique et de la (re)production domestique. Cette analyse se situe dans le cadre d'une problématique construite en termes de rapports sociaux de sexe. Une revue bibliographique des recherches sur le loisir permet de constater que les trois paradigmes thériques qui ont été traditionnellement employés dans l'éude sociologique de ce `fait social' manifestent un biais androcentrique implicite qui pose d' importants problèmes quand il s'agit d'élargir le champ d'analyse de ce phéomène au-delà du rapport travail salarié-loisir qui constitue l'entrée thématique principale de la majorité des recherches existantes dans ce domaine. Bien qu'il ne soit nullement notre intention de proposer une nouvelle conceptualisation théorique du `loisir', l'attention portée sur les différences de sens subjectif et symbolique que les individus et les groupes sociaux attribuent à leurs pratiques de loisir permet, néanmoins, de constater la nature insatisfaisante des recherches fondées sur une analyse quantitative des caractéristiques sociales des pratiquants et soulève la question de l'ètude sociologique des mécanismes de production-reproduction des identités sociales objectives et subjectives qui s'opèrent `a travers les pratiques de loisir. Afin de répondre à cette question, deux approches méthodologiques distinctes ont été adoptées. Les données statistiques portant sur les pratiques `hors-travail' des femmes sont issues d'une enquête effectuée `a l'aide d'un questionnaire ferméaupr`es d'un échantillon non-repréntatif de 157 mères de famille françaises (actives et inactives). Les données sur les représentations temporelles proviennent d'une série de 30 entretiens semi-directifs approfondis effectués auprès de femmes ayant déjà répondu au questionnaire. Une mise en rapport de ces deux types de données permet l'analyse du rôle de l'articulation entre la `part réelle' et la `part pensée' des rapports sociaux de sexe et la conceptualisation du rapport entre les pratiques et les représentations du loisir en fonction de l'inscription objective et subjective des enquêtées dans la hiérarchie sociale de classe et de sexe. De cette analyse découle une définition de la sphère sociale du loisir en tant qu'espace social contesté où se jouent à la fois les mécanismes de reproduction des systèmes des rapports sociaux à l'identique et les mécanismes de réppropriation et de réinterprétation des normes de sexe de la part des groupes sociaux.

Representations of voluntary childlessness in the UK Press, 1990-2008

Representations of voluntary childlessness — the declaration by an individual that he or she does not wish to bear or raise children — were studied in 116 articles published in British national newspapers in the period 1990—2008. Media framing analysis was used to examine broad patterns of framing of the topic, identifying four frames: voluntary childlessness as an individual rights issue, as a form of resistance, as a social trend, and as a personal decision. These frames, it is argued, may act as potential ‘scripts’ for newspaper readers who are debating the decision to start a family.

Looking for redemption in a globalised North:representations of the Arctic in Judith Hermann’s Short Stories Kaltblau (Cold –Blue) and Die Liebe zu Ari Oskarsson (Love for Ari Oskarsson)

This paper explores the literary representation of Iceland and Norway in two short stories by contemporary German writer Judith Hermann. It analyses both the depiction of these countries as part of the globalised western world and the redemptive power they are tentatively ascribed by the author. Continuing a long German tradition of looking at Scandinavia from an almost colonial perspective, Hermann on the one hand presents these northern countries as a mere extension of central Europe, largely devoid of distinguishing national characteristics. At the same time she makes reference to the topos of the north as a vast and empty space and highlights both the specific arctic nature of the environment and the effect it has on her urban characters, who find themselves on a search for meaning and orientation in a postmodern fragmented world. Despite Hermann's overall sceptical attitude towards her characters' quest for happiness, these northern locations ultimately appear as potential places of self-realisation and enlightenment.

The Riesz transform and simultaneous representations of phase, energy and orientation in spatial vision

To represent the local orientation and energy of a 1-D image signal, many models of early visual processing employ bandpass quadrature filters, formed by combining the original signal with its Hilbert transform. However, representations capable of estimating an image signal's 2-D phase have been largely ignored. Here, we consider 2-D phase representations using a method based upon the Riesz transform. For spatial images there exist two Riesz transformed signals and one original signal from which orientation, phase and energy may be represented as a vector in 3-D signal space. We show that these image properties may be represented by a Singular Value Decomposition (SVD) of the higher-order derivatives of the original and the Riesz transformed signals. We further show that the expected responses of even and odd symmetric filters from the Riesz transform may be represented by a single signal autocorrelation function, which is beneficial in simplifying Bayesian computations for spatial orientation. Importantly, the Riesz transform allows one to weight linearly across orientation using both symmetric and asymmetric filters to account for some perceptual phase distortions observed in image signals - notably one's perception of edge structure within plaid patterns whose component gratings are either equal or unequal in contrast. Finally, exploiting the benefits that arise from the Riesz definition of local energy as a scalar quantity, we demonstrate the utility of Riesz signal representations in estimating the spatial orientation of second-order image signals. We conclude that the Riesz transform may be employed as a general tool for 2-D visual pattern recognition by its virtue of representing phase, orientation and energy as orthogonal signal quantities.