Bayesian nonparametric latent variable models

L’un des problèmes importants en apprentissage automatique est de déterminer la complexité du modèle à apprendre. Une trop grande complexité mène au surapprentissage, ce qui correspond à trouver des structures qui n’existent pas réellement dans les données, tandis qu’une trop faible complexité mène au sous-apprentissage, c’est-à-dire que l’expressivité du modèle est insuffisante pour capturer l’ensemble des structures présentes dans les données. Pour certains modèles probabilistes, la complexité du modèle se traduit par l’introduction d’une ou plusieurs variables cachées dont le rôle est d’expliquer le processus génératif des données. Il existe diverses approches permettant d’identifier le nombre approprié de variables cachées d’un modèle. Cette thèse s’intéresse aux méthodes Bayésiennes nonparamétriques permettant de déterminer le nombre de variables cachées à utiliser ainsi que leur dimensionnalité. La popularisation des statistiques Bayésiennes nonparamétriques au sein de la communauté de l’apprentissage automatique est assez récente. Leur principal attrait vient du fait qu’elles offrent des modèles hautement flexibles et dont la complexité s’ajuste proportionnellement à la quantité de données disponibles. Au cours des dernières années, la recherche sur les méthodes d’apprentissage Bayésiennes nonparamétriques a porté sur trois aspects principaux : la construction de nouveaux modèles, le développement d’algorithmes d’inférence et les applications. Cette thèse présente nos contributions à ces trois sujets de recherches dans le contexte d’apprentissage de modèles à variables cachées. Dans un premier temps, nous introduisons le Pitman-Yor process mixture of Gaussians, un modèle permettant l’apprentissage de mélanges infinis de Gaussiennes. Nous présentons aussi un algorithme d’inférence permettant de découvrir les composantes cachées du modèle que nous évaluons sur deux applications concrètes de robotique. Nos résultats démontrent que l’approche proposée surpasse en performance et en flexibilité les approches classiques d’apprentissage. Dans un deuxième temps, nous proposons l’extended cascading Indian buffet process, un modèle servant de distribution de probabilité a priori sur l’espace des graphes dirigés acycliques. Dans le contexte de réseaux Bayésien, ce prior permet d’identifier à la fois la présence de variables cachées et la structure du réseau parmi celles-ci. Un algorithme d’inférence Monte Carlo par chaîne de Markov est utilisé pour l’évaluation sur des problèmes d’identification de structures et d’estimation de densités. Dans un dernier temps, nous proposons le Indian chefs process, un modèle plus général que l’extended cascading Indian buffet process servant à l’apprentissage de graphes et d’ordres. L’avantage du nouveau modèle est qu’il admet les connections entres les variables observables et qu’il prend en compte l’ordre des variables. Nous présentons un algorithme d’inférence Monte Carlo par chaîne de Markov avec saut réversible permettant l’apprentissage conjoint de graphes et d’ordres. L’évaluation est faite sur des problèmes d’estimations de densité et de test d’indépendance. Ce modèle est le premier modèle Bayésien nonparamétrique permettant d’apprendre des réseaux Bayésiens disposant d’une structure complètement arbitraire.

A longitudinal interpretive phenomenological investigation into latent entrepreneurial learning processes: Key implications for entrepreneurial education.

The effectiveness and value of entrepreneurship education is much debated within academic literature. The individual’s experience is advocated as being key to shaping entrepreneurial education and design through a multiplicity of theoretical concepts. Latent, pre-nascent and nascent entrepreneurship (doing) studies within the accepted literature provide an exceptional richness in diversity of thought however, there is a paucity of research into latent entrepreneurship education. In addition, Tolman’s early work shows the existence of cases whereby a novel problem is solved without trial and error, and sees such previous learning situations and circumstances as “examples of latent learning and reasoning”, (Deutsch, 1956, pg115). Latent learning has historically been the cause of much academic debate however, Coon’s (2004, pg260) work refers to “latent (hidden) learning … (as being) … without obvious reinforcement and remains hidden until reinforcement is provided” and thus, forms the working definition for the purpose of this study.

Multiple Imputation of missing values in exploratory factor analysis of multidimensional scales: estimating latent trait scores

ABSTRACT Researchers frequently have to analyze scales in which some participants have failed to respond to some items. In this paper we focus on the exploratory factor analysis of multidimensional scales (i.e., scales that consist of a number of subscales) where each subscale is made up of a number of Likert-type items, and the aim of the analysis is to estimate participants' scores on the corresponding latent traits. We propose a new approach to deal with missing responses in such a situation that is based on (1) multiple imputation of non-responses and (2) simultaneous rotation of the imputed datasets. We applied the approach in a real dataset where missing responses were artificially introduced following a real pattern of non-responses, and a simulation study based on artificial datasets. The results show that our approach (specifically, Hot-Deck multiple imputation followed of Consensus Promin rotation) was able to successfully compute factor score estimates even for participants that have missing data.

Latent semantic indexing eta ikasketa automatikoa hizkuntzaren prozesamenduaren arloan: testu-sailkatzea, hitzen adiera-desanbiguatzea eta korreferentzia-ebaztea SVD bidezko dimentsio murrizketa eta multi-sailkatzailea konbinatuz

220 p.

Multiple solutions and numerical analysis to the dynamic and stationary models coupling a delayed energy balance model involving latent heat and discontinuous albedo with a deep ocean

We study a climatologically important interaction of two of the main components of the geophysical system by adding an energy balance model for the averaged atmospheric temperature as dynamic boundary condition to a diagnostic ocean model having an additional spatial dimension. In this work, we give deeper insight than previous papers in the literature, mainly with respect to the 1990 pioneering model by Watts and Morantine. We are taking into consideration the latent heat for the two phase ocean as well as a possible delayed term. Non-uniqueness for the initial boundary value problem, uniqueness under a non-degeneracy condition and the existence of multiple stationary solutions are proved here. These multiplicity results suggest that an S-shaped bifurcation diagram should be expected to occur in this class of models generalizing previous energy balance models. The numerical method applied to the model is based on a finite volume scheme with nonlinear weighted essentially non-oscillatory reconstruction and Runge–Kutta total variation diminishing for time integration.

AUTOMATIC LABELING OF RSS ARTICLES USING ONLINE LATENT DIRICHLET ALLOCATION

The amount of information contained within the Internet has exploded in recent decades. As more and more news, blogs, and many other kinds of articles that are published on the Internet, categorization of articles and documents are increasingly desired. Among the approaches to categorize articles, labeling is one of the most common method; it provides a relatively intuitive and effective way to separate articles into different categories. However, manual labeling is limited by its efficiency, even thought the labels selected manually have relatively high quality. This report explores the topic modeling approach of Online Latent Dirichlet Allocation (Online-LDA). Additionally, a method to automatically label articles with their latent topics by combining the Online-LDA posterior with a probabilistic automatic labeling algorithm is implemented. The goal of this report is to examine the accuracy of the labels generated automatically by a topic model and probabilistic relevance algorithm for a set of real-world, dynamically updated articles from an online Rich Site Summary (RSS) service.

A novel latent factor model for recommender system

Matrix factorization (MF) has evolved as one of the better practice to handle sparse data in field of recommender systems. Funk singular value decomposition (SVD) is a variant of MF that exists as state-of-the-art method that enabled winning the Netflix prize competition. The method is widely used with modifications in present day research in field of recommender systems. With the potential of data points to grow at very high velocity, it is prudent to devise newer methods that can handle such data accurately as well as efficiently than Funk-SVD in the context of recommender system. In view of the growing data points, I propose a latent factor model that caters to both accuracy and efficiency by reducing the number of latent features of either users or items making it less complex than Funk-SVD, where latent features of both users and items are equal and often larger. A comprehensive empirical evaluation of accuracy on two publicly available, amazon and ml-100 k datasets reveals the comparable accuracy and lesser complexity of proposed methods than Funk-SVD.

In search of a theory of integrated marketing communication

For the most part, the literature base for Integrated Marketing Communication (IMC) has developed from an applied or tactical level rather than from an intellectual or theoretical one. Since industry, practitioner and even academic studies have provided little insight into what IMC is and how it operates, our approach has been to investigate that other IMC community, that is, the academic or instructional group responsible for disseminating IMC knowledge. We proposed that the people providing course instruction and directing research activities have some basis for how they organize, consider and therefore instruct in the area of IMC. A syllabi analysis of 87 IMC units in six countries investigated the content of the unit, its delivery both physically and conceptually, and defined the audience of the unit. The study failed to discover any type of latent theoretical foundation that might be used as a base for understanding IMC. The students who are being prepared to extend, expand and enhance IMC concepts do not appear to be well-served by the curriculum we found in our research. The study concludes with a model for further IMC curriculum development.

User-designer collaboration during the early stage of the product development process

As an understanding of users' tacit knowledge and latent needs embedded in user experience has played a critical role in product development, users’ direct involvement in design has become a necessary part of the design process. Various ways of accessing users' tacit knowledge and latent needs have been explored in the field of user-centred design, participatory design, and design for experiencing. User-designer collaboration has been used unconsciously by traditional designers to facilitate the transfer of users' tacit knowledge and to elicit new knowledge. However, what makes user-designer collaboration an effective strategy has rarely been reported on or explored. Therefore, interaction patterns between the users and the designers in three industry-supported user involvement cases were studied. In order to develop a coding system, collaboration was defined as a set of coordinated and joint problem solving activities, measured by the elicitation of new knowledge from collaboration. The analysis of interaction patterns in the user involvement cases revealed that allowing users to challenge or modify their contextual experiences facilitates the transfer of knowledge and new knowledge generation. It was concluded that users can be more effectively integrated into the product development process by employing collaboration strategies to intensify the depth of user involvement.

Effective web service discovery using a combination of a semantic model and a data mining technique

With the advent of Service Oriented Architecture, Web Services have gained tremendous popularity. Due to the availability of a large number of Web services, finding an appropriate Web service according to the requirement of the user is a challenge. This warrants the need to establish an effective and reliable process of Web service discovery. A considerable body of research has emerged to develop methods to improve the accuracy of Web service discovery to match the best service. The process of Web service discovery results in suggesting many individual services that partially fulfil the user’s interest. By considering the semantic relationships of words used in describing the services as well as the use of input and output parameters can lead to accurate Web service discovery. Appropriate linking of individual matched services should fully satisfy the requirements which the user is looking for. This research proposes to integrate a semantic model and a data mining technique to enhance the accuracy of Web service discovery. A novel three-phase Web service discovery methodology has been proposed. The first phase performs match-making to find semantically similar Web services for a user query. In order to perform semantic analysis on the content present in the Web service description language document, the support-based latent semantic kernel is constructed using an innovative concept of binning and merging on the large quantity of text documents covering diverse areas of domain of knowledge. The use of a generic latent semantic kernel constructed with a large number of terms helps to find the hidden meaning of the query terms which otherwise could not be found. Sometimes a single Web service is unable to fully satisfy the requirement of the user. In such cases, a composition of multiple inter-related Web services is presented to the user. The task of checking the possibility of linking multiple Web services is done in the second phase. Once the feasibility of linking Web services is checked, the objective is to provide the user with the best composition of Web services. In the link analysis phase, the Web services are modelled as nodes of a graph and an allpair shortest-path algorithm is applied to find the optimum path at the minimum cost for traversal. The third phase which is the system integration, integrates the results from the preceding two phases by using an original fusion algorithm in the fusion engine. Finally, the recommendation engine which is an integral part of the system integration phase makes the final recommendations including individual and composite Web services to the user. In order to evaluate the performance of the proposed method, extensive experimentation has been performed. Results of the proposed support-based semantic kernel method of Web service discovery are compared with the results of the standard keyword-based information-retrieval method and a clustering-based machine-learning method of Web service discovery. The proposed method outperforms both information-retrieval and machine-learning based methods. Experimental results and statistical analysis also show that the best Web services compositions are obtained by considering 10 to 15 Web services that are found in phase-I for linking. Empirical results also ascertain that the fusion engine boosts the accuracy of Web service discovery by combining the inputs from both the semantic analysis (phase-I) and the link analysis (phase-II) in a systematic fashion. Overall, the accuracy of Web service discovery with the proposed method shows a significant improvement over traditional discovery methods.

Beyond Bryan: Builders' liability and pure economic loss

In Bryan v Maloney, the High Court extended a builder’s duty of care to encompass a liability in negligence for the pure economic loss sustained by a subsequent purchaser of a residential dwelling as a result of latent defects in the building’s construction. Recently, in Woolcock Street Investments Pty Ltd v CDG Pty Ltd, the Court refused to extend this liability to defects in commercial premises. The decision therefore provides an opportunity to re-examine the rationale and policy behind current jurisprudence governing builders’ liability for pure economic loss. In doing so, this article considers the principles relevant to the determination of a duty of care generally and whether the differences between purchasers of residential and commercial properties are as great as the case law suggests

A review of LCADesign

Objective The review addresses two distinct sets of issues: 1. specific functionality, interface, and calculation problems that presumably can be fixed or improved; and 2. the more fundamental question of whether the system is close to being ready for ‘commercial prime time’ in the North American market. Findings Many of our comments relate to the first set of issues, especially sections B and C. Sections D and E deal with the second set. Overall, we feel that LCADesign represents a very impressive step forward in the ongoing quest to link CAD with LCA tools and, more importantly, to link the world of architectural practice and that of environmental research. From that perspective, it deserves continued financial support as a research project. However, if the decision is whether or not to continue the development program from a purely commercial perspective, we are less bullish. In terms of the North American market, there are no regulatory or other drivers to press design teams to use a tool of this nature. There is certainly interest in this area, but the tools must be very easy to use with little or no training. Understanding the results is as important in this regard as knowing how to apply the tool. Our comments are fairly negative when it comes to that aspect. Our opinion might change to some degree when the ‘fixes’ are made and the functionality improved. However, as discussed in more detail in the following sections, we feel that the multi-step process — CAD to IFC to LCADesign — could pose a serious problem in terms of market acceptance. The CAD to IFC part is impossible for us to judge with the information provided, and we can’t even begin to answer the question about the ease of using the software to import designs, but it appears cumbersome from what we do know. There does appear to be a developing North American market for 3D CAD, with a recent survey indicating that about 50% of the firms use some form of 3D modeling for about 75% of their projects. However, this does not mean that full 3D CAD is always being used. Our information suggests that AutoDesk accounts for about 75 to 80% of the 3D CAD market, and they are very cautious about any links that do not serve a latent demand. Finally, other system that link CAD to energy simulation are using XML data transfer protocols rather than IFC files, and it is our understanding that the market served by AutoDesk tends in that direction right now. This is a subject that is outside our area of expertise, so please take these comments as suggestions for more intensive market research rather than as definitive findings.

Early detection : a strategy to reduce risk and severity?

Despite changes in surgical techniques, radiotherapy targeting and the apparent earlier detection of cancers, secondary lymphoedema is still a significant problem for about 20–30% of those who receive treatment for cancer, although the incidence and prevalence does seem to be falling. The figures above generally relate to detection of an enlarged limb or other area, but it seems that about 60% of all patients also suffer other problems with how the limb feels, what can or cannot be done with it and a range of social or psychological issues. Often these ‘subjective’ changes occur before the objective ones, such as a change in arm volume or circumference. For most of those treated for cancer lymphoedema does not develop immediately, and, while about 60–70% develop it in the first few years, some do not develop lymphoedema for up to 15 or 20 years. Those who will develop clinically manifest lymphoedema in the future are, for some time, in a latent or hidden phase of lymphoedema. There also seems to be some risk factors which are indicators for a higher likelihood of lymphoedema post treatment, including oedema at the surgical site, arm dominance, age, skin conditions, and body mass index (BMI).