Using directional curvatures to visualize folding patterns of the GTM projection manifolds

In data visualization, characterizing local geometric properties of non-linear projection manifolds provides the user with valuable additional information that can influence further steps in the data analysis. We take advantage of the smooth character of GTM projection manifold and analytically calculate its local directional curvatures. Curvature plots are useful for detecting regions where geometry is distorted, for changing the amount of regularization in non-linear projection manifolds, and for choosing regions of interest when constructing detailed lower-level visualization plots.

Hierarchical GTM: constructing localized non-linear projection manifolds in a principled way

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 ¸iteBishop98a in several directions: bf(1) We allow for em non-linear projection manifolds. The basic building block is the Generative Topographic Mapping (GTM). bf(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. bf(3) Using tools from differential geometry we derive expressions for local directional curvatures 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 ancestor visualization plots 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 and apply our system to two more complex 12- and 18-dimensional data sets.

A principled approach to interactive hierarchical non-linear visualization of high-dimensional data

Hierarchical visualization systems are desirable because a single two-dimensional visualization plot may not be sufficient to capture all of the interesting aspects of complex high-dimensional data sets. We extend an existing locally linear hierarchical visualization system PhiVis [1] in several directions: bf(1) we allow for em non-linear projection manifolds (the basic building block is the Generative Topographic Mapping -- GTM), bf(2) we introduce a general formulation of hierarchical probabilistic models consisting of local probabilistic models organized in a hierarchical tree, bf(3) we describe folding patterns of low-dimensional projection manifold in high-dimensional data space by computing and visualizing the manifold's local directional curvatures. Quantities such as magnification factors [3] and directional curvatures are helpful for understanding the layout of the nonlinear projection manifold in the data space and for further refinement of the hierarchical visualization plot. Like PhiVis, our system is statistically principled and is built interactively in a top-down fashion using the EM algorithm. We demonstrate the visualization system principle of the approach on a complex 12-dimensional data set and mention possible applications in the pharmaceutical industry.

Semi-supervised construction of general visualization hierarchies

We have recently developed a principled approach to interactive non-linear hierarchical visualization [8] based on the Generative Topographic Mapping (GTM). Hierarchical plots are needed when a single visualization plot is not sufficient (e.g. when dealing with large quantities of data). In this paper we extend our system by giving the user a choice of initializing the child plots of the current plot in either interactive, or automatic mode. In the interactive mode the user interactively selects ``regions of interest'' as in [8], whereas in the automatic mode an unsupervised minimum message length (MML)-driven construction of a mixture of GTMs is used. The latter is particularly useful when the plots are covered with dense clusters of highly overlapping data projections, making it difficult to use the interactive mode. Such a situation often arises when visualizing large data sets. We illustrate our approach on a data set of 2300 18-dimensional points and mention extension of our system to accommodate discrete data types.

Semi-supervised learning of hierarchical latent trait models for data visualisation

An interactive hierarchical Generative Topographic Mapping (HGTM) ¸iteH_GTM has been developed to visualise complex data sets. In this paper, we build a more general visualisation system by extending the HGTM visualisation system in 3 directions: bf (1) We generalize HGTM to noise models from the exponential family of distributions. The basic building block is the Latent Trait Model (LTM) developed in ¸iteKaban_pami. bf (2) We give the user a choice of initializing the child plots of the current plot in either em interactive, or em automatic mode. In the interactive mode the user interactively selects ``regions of interest'' as in ¸iteH_GTM, whereas in the automatic mode an unsupervised minimum message length (MML)-driven construction of a mixture of LTMs is employed. bf (3) We derive general formulas for magnification factors in latent trait models. Magnification factors are a useful tool to improve our understanding of the visualisation plots, since they can highlight the boundaries between data clusters. The unsupervised construction is particularly useful when high-level plots are covered with dense clusters of highly overlapping data projections, making it difficult to use the interactive mode. Such a situation often arises when visualizing large data sets. We illustrate our approach on a toy example and apply our system to three more complex real data sets.

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.

Dynamics and topographic organization of recursive self-organizing maps

Recently there has been an outburst of interest in extending topographic maps of vectorial data to more general data structures, such as sequences or trees. However, there is no general consensus as to how best to process sequences using topographicmaps, and this topic remains an active focus of neurocomputational research. The representational capabilities and internal representations of the models are not well understood. Here, we rigorously analyze a generalization of the self-organizingmap (SOM) for processing sequential data, recursive SOM (RecSOM) (Voegtlin, 2002), as a nonautonomous dynamical system consisting of a set of fixed input maps. We argue that contractive fixed-input maps are likely to produce Markovian organizations of receptive fields on the RecSOM map. We derive bounds on parameter β (weighting the importance of importing past information when processing sequences) under which contractiveness of the fixed-input maps is guaranteed. Some generalizations of SOM contain a dynamic module responsible for processing temporal contexts as an integral part of the model. We show that Markovian topographic maps of sequential data can be produced using a simple fixed (nonadaptable) dynamic module externally feeding a standard topographic model designed to process static vectorial data of fixed dimensionality (e.g., SOM). However, by allowing trainable feedback connections, one can obtain Markovian maps with superior memory depth and topography preservation. We elaborate on the importance of non-Markovian organizations in topographic maps of sequential data. © 2006 Massachusetts Institute of Technology.

Does money matter in inflation forecasting

This paper provides the most fully comprehensive evidence to date on whether or not monetary aggregates are valuable for forecasting US inflation in the early to mid 2000s. We explore a wide range of different definitions of money, including different methods of aggregation and different collections of included monetary assets. In our forecasting experiment we use two non-linear techniques, namely, recurrent neural networks and kernel recursive least squares regression - techniques that are new to macroeconomics. Recurrent neural networks operate with potentially unbounded input memory, while the kernel regression technique is a finite memory predictor. The two methodologies compete to find the best fitting US inflation forecasting models and are then compared to forecasts from a naive random walk model. The best models were non-linear autoregressive models based on kernel methods. Our findings do not provide much support for the usefulness of monetary aggregates in forecasting inflation.

Margetinggeschichte:Die Genese einer modernen Sozialtechnik, Hartmut Berghoff

Book revew: Marketinggeschichte: die Genese einer modernen Sozialtechnik [Marketing history: The genesis of a modern social technique], edited by Hartmut Berghoff, Frankfurt/Main, Campus Verlag, 2007, 409 pp., illus., [euro]30.00 (paperback), ISBN 978-3-593-38323-1. This edited volume is the result of a workshop at Göttingen University in 2006 and combines a number of different approaches to the research into the history of marketing in Germany's economy and society. The majority of contributions loosely focus around the occurrence of a ‘marketing revolution’ in the 1970s, which ties in with interpretations of the Americanisation of German business. This revolution replaced the indigenous German idea of Absatzwirtschaft (the economics of sales) with the American-influenced idea of Marketing, which was less functionally oriented and more strategic, and which aimed to connect processes within the firm in order to allow a greater focus on the consumer. The entire volume is framed by Hartmut Berghoff's substantial and informative introduction, which introduces a number of actors and trends beyond the content of the volume. Throughout the various contributions, authors provide explanations of the timing and nature of marketing revolutions. Alexander Engel identifies an earlier revolution in the marketing of dyes, which undergoes major change with the emergence of chemical dyes. While the natural dyestuff had been a commodity, with producers removed from consumers via a global network of traders, chemical dyes were products and were branded at an early stage. This was a fundamental change in the nature of production and sales. As Roman Rossfeld shows in his contribution on the Swiss chocolate industry (which focuses almost exclusively on Suchard), even companies that produced non-essential consumer goods which had always required some measure of labelling grappled for years with the need to develop fewer and higher impact brands, as well as an efficient sales operation. A good example for the classical ‘marketing revolution’ of the 1970s is the German automobile industry. Ingo Köhler convincingly argues that the crisis situation of German car manufacturers – the change from a seller's to a buyer's market, appreciation of the German mark which undermines exports, the oil crises coupled with higher inflation and greater frugality of consumers and the emergence of new competitors – lead companies to refocus from production to the demands of the consumer. While he highlights the role of Ford in responding most rapidly to these problems, he does not address whether the multinational was potentially transferring American knowledge to the German market. Similarly, Paul Erker illustrates that a marketing revolution in transport and logistics happened much later, because the market remained highly regulated until the 1980s. Both Paul Erker and Uwe Spiekermann in their contribution, present comparisons of two different sectors or companies (the tire manufacturer Continental and the logistics company Dachser, and agriculture and trade, respectively). In both cases, however, it remains unclear why these examples were chosen for comparison, as both seem to have little in common and are not always effectively used to demonstrate differences. The weakest section of the book is the development of marketing as an academic discipline. The attempt at sketching the phases in the evolution of marketing as an academic discipline by Ursula Hansen and Matthias Bode opens with an undergraduate-level explanation on the methodology of historical periodisation that seems extraneous. Considerably stronger is the section on the wider societal impact of marketing, and Anja Kruke shows how the new techniques of opinion research was accepted by politics and business – surprisingly more readily by politicians than their commercial counterparts. In terms of contemporary personalities, Hans Domizlaff emerges as one fascinating figure of German marketing history, which several contributors refer to and whose career as the German cigarette manufacturer Reemtsma is critically analysed by Tino Jacobs. Domizlaff was Germany's own ‘marketing guru’, whose successful campaigns led to the wide-ranging reception of his ideas about the nature of good branding and marketing. These are variously described as intuitive, elitist, and sachlich, a German concept of a sober, fact-based, and ‘no frills’ approach. Domizlaff did not believe in market research. Rather, he saw the genius of the individual advertiser as key to intuitively ascertaining the people's moods, wishes, and desires. This seems to have made him peculiarly suited to the tastes of the German middle class, according to Thomas Mergel's contribution on the nature of political marketing in the republic. Especially in politics, any form of hard sales tactics were severely frowned upon and considered to demean the citizen as incapable of making an informed choice, a mentality that he dates back to the traditions of nineteenth-century liberalism. Part of this disdain of ‘selling politics like toothpaste’ was also founded on the highly effective use of branding by the National Socialists, who identified their party through the use of an increasingly standardised image of Adolf Hitler and the swastika. Alexander Schug extends on previous research that criticised the simplistic notion of Hitler's charisma as the only explanation of the popular success and distances his approach from those who see it in terms of propaganda and demagogy. He argues that the NSDAP used the tools of advertising and branding precisely because they had to introduce their new ideology into a political marketplace dominated by more established parties. In this they were undoubtedly successful, more so than they intended: as bakers sold swastika cookies and butchers formed Führer heads out of lard, the NSDAP sought to regain control over the now effectively iconic images that constituted their brand, which was in danger of being trivialised and devalued. Key to understanding the history of marketing in Germany is on the one hand the exchange of ideas with the United States, and on the other the impact of national-socialist policies, and the question whether they were a force of modernisation or retardation. The general argument in the volume appears to favour the latter explanation. In the 1930s, some of the leading marketing experts emigrated to the USA, leaving German academia and business isolated. The aftermath of the Second World War left a country that needed to increase production to satisfy consumer demand, and there was little interest in advanced sales techniques. Although the Nazis were progressive in applying new marketing methods to their political campaign, this retarded the adoption of sales techniques in politics for a long time. Germany saw the development of idiosyncratic approaches by people like Domizlaff in the 1930s and 1940s, when it lost some leading thinkers, and only engaged with American marketing conceptions in the 1960s and 1970s, when consumers eventually became more important than producers.

Evolution, recurrency and kernels in learning to model inflation

This paper provides the most fully comprehensive evidence to date on whether or not monetary aggregates are valuable for forecasting US inflation in the early to mid 2000s. We explore a wide range of different definitions of money, including different methods of aggregation and different collections of included monetary assets. We use non-linear, artificial intelligence techniques, namely, recurrent neural networks, evolution strategies and kernel methods in our forecasting experiment. In the experiment, these three methodologies compete to find the best fitting US inflation forecasting models and are then compared to forecasts from a naive random walk model. The best models were non-linear autoregressive models based on kernel methods. Our findings do not provide much support for the usefulness of monetary aggregates in forecasting inflation. There is evidence in the literature that evolutionary methods can be used to evolve kernels hence our future work should combine the evolutionary and kernel methods to get the benefits of both.

Coupled symplectic maps as models for subdiffusive processes in disordered Hamiltonian lattices

Acknowledgements One of us (T. B.) acknowledges many interesting discussions on coupled maps with Professor C. Tsallis. We are also grateful to the anonymous referees for their constructive feedback that helped us improve the manuscript and to the HPCS Laboratory of the TEI of Western Greece for providing the computer facilities where all our simulations were performed. C. G. A. was partially supported by the “EPSRC EP/I032606/1” grant of the University of Aberdeen. This research has been co-financed by the European Union (European Social Fund - ESF) and Greek national funds through the Operational Program “Education and Lifelong Learning” of the National Strategic Reference Framework (NSRF) - Research Funding Program: THALES - Investing in knowledge society through the European Social Fund.

Coupled symplectic maps as models for subdiffusive processes in disordered Hamiltonian lattices

Acknowledgements One of us (T. B.) acknowledges many interesting discussions on coupled maps with Professor C. Tsallis. We are also grateful to the anonymous referees for their constructive feedback that helped us improve the manuscript and to the HPCS Laboratory of the TEI of Western Greece for providing the computer facilities where all our simulations were performed. C. G. A. was partially supported by the “EPSRC EP/I032606/1” grant of the University of Aberdeen. This research has been co-financed by the European Union (European Social Fund - ESF) and Greek national funds through the Operational Program “Education and Lifelong Learning” of the National Strategic Reference Framework (NSRF) - Research Funding Program: THALES - Investing in knowledge society through the European Social Fund.

Macroscopic Quantum Resonators (MAQRO): 2015 update

Do the laws of quantum physics still hold for macroscopic objects - this is at the heart of Schrödinger’s cat paradox - or do gravitation or yet unknown effects set a limit for massive particles? What is the fundamental relation between quantum physics and gravity? Ground-based experiments addressing these questions may soon face limitations due to limited free-fall times and the quality of vacuum and microgravity. The proposed mission Macroscopic Quantum Resonators (MAQRO) may overcome these limitations and allow addressing such fundamental questions. MAQRO harnesses recent developments in quantum optomechanics, high-mass matter-wave interferometry as well as state-of-the-art space technology to push macroscopic quantum experiments towards their ultimate performance limits and to open new horizons for applying quantum technology in space. The main scientific goal is to probe the vastly unexplored ‘quantum-classical’ transition for increasingly massive objects, testing the predictions of quantum theory for objects in a size and mass regime unachievable in ground-based experiments. The hardware will largely be based on available space technology. Here, we present the MAQRO proposal submitted in response to the 4th Cosmic Vision call for a medium-sized mission (M4) in 2014 of the European Space Agency (ESA) with a possible launch in 2025, and we review the progress with respect to the original MAQRO proposal for the 3rd Cosmic Vision call for a medium-sized mission (M3) in 2010. In particular, the updated proposal overcomes several critical issues of the original proposal by relying on established experimental techniques from high-mass matter-wave interferometry and by introducing novel ideas for particle loading and manipulation. Moreover, the mission design was improved to better fulfill the stringent environmental requirements for macroscopic quantum experiments.