Bayesian network classifiers: Beyond classification accuracy

This work proposes and discusses an approach for inducing Bayesian classifiers aimed at balancing the tradeoff between the precise probability estimates produced by time consuming unrestricted Bayesian networks and the computational efficiency of Naive Bayes (NB) classifiers. The proposed approach is based on the fundamental principles of the Heuristic Search Bayesian network learning. The Markov Blanket concept, as well as a proposed ""approximate Markov Blanket"" are used to reduce the number of nodes that form the Bayesian network to be induced from data. Consequently, the usually high computational cost of the heuristic search learning algorithms can be lessened, while Bayesian network structures better than NB can be achieved. The resulting algorithms, called DMBC (Dynamic Markov Blanket Classifier) and A-DMBC (Approximate DMBC), are empirically assessed in twelve domains that illustrate scenarios of particular interest. The obtained results are compared with NB and Tree Augmented Network (TAN) classifiers, and confinn that both proposed algorithms can provide good classification accuracies and better probability estimates than NB and TAN, while being more computationally efficient than the widely used K2 Algorithm.

Evolutionary structure learning algorithm for Bayesian network and penalized mutual information metric

This paper formulates the problem of learning Bayesian network structures from data as determining the structure that best approximates the probability distribution indicated by the data. A new metric, Penalized Mutual Information metric, is proposed, and a evolutionary algorithm is designed to search for the best structure among alternatives. The experimental results show that this approach is reliable and promising.

Learning dependency model for AMP-activated protein kinase regulation

The AMP-activated protein kinase (AMPK) acts as a metabolic master switch regulating several intracellular systems. The effect of AMPK on muscle cellular energy status makes this protein a promising pharmacological target for disease treatment. With increasingly available AMPK regulation data, it is critical to develop an efficient way to analyze the data since this assists in further understanding AMPK pathways. Bayesian networks can play an important role in expressing the dependency and causality in the data. This paper aims to analyse the regulation data using B-Course, a powerful analysis tool to exploit several theoretically elaborate results in the fields of Bayesian and causal modelling, and discover a certain type of multivariate probabilistic dependencies. The identified dependency models are easier to understand in comparison with the traditional frequent patterns.

Case study of e-learning experts in Malaysia : impact of social capital and social networks

This paper examines the experiences of selected academics pioneering e-learning in Malaysian tertiary institutions. It begins with an overview of the broad factors shaping the Malaysian educational environment and then proceeds to examine the experience of individual teachers and e-learning programs. It takes an in-depth qualitative approach to engaging with this case study material drawing heavily on semi-structured interviews with key actors.
Conversations with several respondents suggested that the social networks of mentor relations found in the Malaysian case studies might be aptly described as ‘bamboo networks’. Bamboo, which happens to be plentiful in the Malaysian peninsula where these case studies are based, spreads from clump to clump through a series of underground connections involving a mature clump of bamboo sending out a subterranean runner, often over very long distances that then emerge into the open as a new bamboo clump.
All of those interviewed reported that they have found it difficult to find a support base in their first years of pioneering online developments. Consequently, they tended to fall back on their peer networks linked to the institutions at which they had studied. Prominent individuals championing e-learning in the institutions where they teach tend to form small groups for information sharing and networking. They do look to their management for tacit ‘permission’ rather than direct encouragement. Consequently, the active promotion of e-learning in Malaysia can be described as being ‘middle-down’ rather than ‘top-down’ in nature. That is to say, it is mid-level teachers that inspire those below them to join in the development of e-learning programs. They are internally driven and strongly motivated. In time, their activity should produce new generations of locally developed e-learning experts but this has yet to take place in a substantial fashion. This study shows that both men and women ‘academic guanxi’, or peer networks, play a key role in the adoption of online technologies. Key early adopters become change-agents by inspiring a small network of their peers and via their guanxi networks. It was also discovered that motivation is not simply an individual matter but is also about groups and peer networks or communities of exchange and encouragement. In the development of e-learning in Malaysia, there is very little activity that is not linked to small clusters of developers who are tied into wider networks through personal contacts.
Like clumping bamboo, whilst the local clusters tend to be easily seen, the longer-range ‘subterranean’ personal connections are generally not nearly so immediately obvious. These connections are often the product of previous mentoring relationships, including the relationships between influential teachers and their former postgraduate students. These relationships tend to work like bamboo runners: they run off in multiple directions, subterranean and unseen and then throw up new clumps that then send out fresh runners of their own.

Structure learning of graphical models for task-oriented robot grasping

In the collective imaginaries a robot is a human like machine as any androids in science fiction. However the type of robots that you will encounter most frequently are machinery that do work that is too dangerous, boring or onerous. Most of the robots in the world are of this type. They can be found in auto, medical, manufacturing and space industries. Therefore a robot is a system that contains sensors, control systems, manipulators, power supplies and software all working together to perform a task. The development and use of such a system is an active area of research and one of the main problems is the development of interaction skills with the surrounding environment, which include the ability to grasp objects. To perform this task the robot needs to sense the environment and acquire the object informations, physical attributes that may influence a grasp. Humans can solve this grasping problem easily due to their past experiences, that is why many researchers are approaching it from a machine learning perspective finding grasp of an object using information of already known objects. But humans can select the best grasp amongst a vast repertoire not only considering the physical attributes of the object to grasp but even to obtain a certain effect. This is why in our case the study in the area of robot manipulation is focused on grasping and integrating symbolic tasks with data gained through sensors. The learning model is based on Bayesian Network to encode the statistical dependencies between the data collected by the sensors and the symbolic task. This data representation has several advantages. It allows to take into account the uncertainty of the real world, allowing to deal with sensor noise, encodes notion of causality and provides an unified network for learning. Since the network is actually implemented and based on the human expert knowledge, it is very interesting to implement an automated method to learn the structure as in the future more tasks and object features can be introduced and a complex network design based only on human expert knowledge can become unreliable. Since structure learning algorithms presents some weaknesses, the goal of this thesis is to analyze real data used in the network modeled by the human expert, implement a feasible structure learning approach and compare the results with the network designed by the expert in order to possibly enhance it.

Regularization for sparsity in statistical analysis and machine learning

Pragmatism is the leading motivation of regularization. We can understand regularization as a modification of the maximum-likelihood estimator so that a reasonable answer could be given in an unstable or ill-posed situation. To mention some typical examples, this happens when fitting parametric or non-parametric models with more parameters than data or when estimating large covariance matrices. Regularization is usually used, in addition, to improve the bias-variance tradeoff of an estimation. Then, the definition of regularization is quite general, and, although the introduction of a penalty is probably the most popular type, it is just one out of multiple forms of regularization. In this dissertation, we focus on the applications of regularization for obtaining sparse or parsimonious representations, where only a subset of the inputs is used. A particular form of regularization, L1-regularization, plays a key role for reaching sparsity. Most of the contributions presented here revolve around L1-regularization, although other forms of regularization are explored (also pursuing sparsity in some sense). In addition to present a compact review of L1-regularization and its applications in statistical and machine learning, we devise methodology for regression, supervised classification and structure induction of graphical models. Within the regression paradigm, we focus on kernel smoothing learning, proposing techniques for kernel design that are suitable for high dimensional settings and sparse regression functions. We also present an application of regularized regression techniques for modeling the response of biological neurons. Supervised classification advances deal, on the one hand, with the application of regularization for obtaining a na¨ıve Bayes classifier and, on the other hand, with a novel algorithm for brain-computer interface design that uses group regularization in an efficient manner. Finally, we present a heuristic for inducing structures of Gaussian Bayesian networks using L1-regularization as a filter. El pragmatismo es la principal motivación de la regularización. Podemos entender la regularización como una modificación del estimador de máxima verosimilitud, de tal manera que se pueda dar una respuesta cuando la configuración del problema es inestable. A modo de ejemplo, podemos mencionar el ajuste de modelos paramétricos o no paramétricos cuando hay más parámetros que casos en el conjunto de datos, o la estimación de grandes matrices de covarianzas. Se suele recurrir a la regularización, además, para mejorar el compromiso sesgo-varianza en una estimación. Por tanto, la definición de regularización es muy general y, aunque la introducción de una función de penalización es probablemente el método más popular, éste es sólo uno de entre varias posibilidades. En esta tesis se ha trabajado en aplicaciones de regularización para obtener representaciones dispersas, donde sólo se usa un subconjunto de las entradas. En particular, la regularización L1 juega un papel clave en la búsqueda de dicha dispersión. La mayor parte de las contribuciones presentadas en la tesis giran alrededor de la regularización L1, aunque también se exploran otras formas de regularización (que igualmente persiguen un modelo disperso). Además de presentar una revisión de la regularización L1 y sus aplicaciones en estadística y aprendizaje de máquina, se ha desarrollado metodología para regresión, clasificación supervisada y aprendizaje de estructura en modelos gráficos. Dentro de la regresión, se ha trabajado principalmente en métodos de regresión local, proponiendo técnicas de diseño del kernel que sean adecuadas a configuraciones de alta dimensionalidad y funciones de regresión dispersas. También se presenta una aplicación de las técnicas de regresión regularizada para modelar la respuesta de neuronas reales. Los avances en clasificación supervisada tratan, por una parte, con el uso de regularización para obtener un clasificador naive Bayes y, por otra parte, con el desarrollo de un algoritmo que usa regularización por grupos de una manera eficiente y que se ha aplicado al diseño de interfaces cerebromáquina. Finalmente, se presenta una heurística para inducir la estructura de redes Bayesianas Gaussianas usando regularización L1 a modo de filtro.

Regularized model learning in EDAs for continuous and multi-objective optimization

Probabilistic modeling is the de�ning characteristic of estimation of distribution algorithms (EDAs) which determines their behavior and performance in optimization. Regularization is a well-known statistical technique used for obtaining an improved model by reducing the generalization error of estimation, especially in high-dimensional problems. `1-regularization is a type of this technique with the appealing variable selection property which results in sparse model estimations. In this thesis, we study the use of regularization techniques for model learning in EDAs. Several methods for regularized model estimation in continuous domains based on a Gaussian distribution assumption are presented, and analyzed from di�erent aspects when used for optimization in a high-dimensional setting, where the population size of EDA has a logarithmic scale with respect to the number of variables. The optimization results obtained for a number of continuous problems with an increasing number of variables show that the proposed EDA based on regularized model estimation performs a more robust optimization, and is able to achieve signi�cantly better results for larger dimensions than other Gaussian-based EDAs. We also propose a method for learning a marginally factorized Gaussian Markov random �eld model using regularization techniques and a clustering algorithm. The experimental results show notable optimization performance on continuous additively decomposable problems when using this model estimation method. Our study also covers multi-objective optimization and we propose joint probabilistic modeling of variables and objectives in EDAs based on Bayesian networks, speci�cally models inspired from multi-dimensional Bayesian network classi�ers. It is shown that with this approach to modeling, two new types of relationships are encoded in the estimated models in addition to the variable relationships captured in other EDAs: objectivevariable and objective-objective relationships. An extensive experimental study shows the e�ectiveness of this approach for multi- and many-objective optimization. With the proposed joint variable-objective modeling, in addition to the Pareto set approximation, the algorithm is also able to obtain an estimation of the multi-objective problem structure. Finally, the study of multi-objective optimization based on joint probabilistic modeling is extended to noisy domains, where the noise in objective values is represented by intervals. A new version of the Pareto dominance relation for ordering the solutions in these problems, namely �-degree Pareto dominance, is introduced and its properties are analyzed. We show that the ranking methods based on this dominance relation can result in competitive performance of EDAs with respect to the quality of the approximated Pareto sets. This dominance relation is then used together with a method for joint probabilistic modeling based on `1-regularization for multi-objective feature subset selection in classi�cation, where six di�erent measures of accuracy are considered as objectives with interval values. The individual assessment of the proposed joint probabilistic modeling and solution ranking methods on datasets with small-medium dimensionality, when using two di�erent Bayesian classi�ers, shows that comparable or better Pareto sets of feature subsets are approximated in comparison to standard methods.

Multi-dimensional classification of GABAergic interneurons with Bayesian network-modeled label uncertainty

Abstract Interneuron classification is an important and long-debated topic in neuroscience. A recent study provided a data set of digitally reconstructed interneurons classified by 42 leading neuroscientists according to a pragmatic classification scheme composed of five categorical variables, namely, of the interneuron type and four features of axonal morphology. From this data set we now learned a model which can classify interneurons, on the basis of their axonal morphometric parameters, into these five descriptive variables simultaneously. Because of differences in opinion among the neuroscientists, especially regarding neuronal type, for many interneurons we lacked a unique, agreed-upon classification, which we could use to guide model learning. Instead, we guided model learning with a probability distribution over the neuronal type and the axonal features, obtained, for each interneuron, from the neuroscientists’ classification choices. We conveniently encoded such probability distributions with Bayesian networks, calling them label Bayesian networks (LBNs), and developed a method to predict them. This method predicts an LBN by forming a probabilistic consensus among the LBNs of the interneurons most similar to the one being classified. We used 18 axonal morphometric parameters as predictor variables, 13 of which we introduce in this paper as quantitative counterparts to the categorical axonal features. We were able to accurately predict interneuronal LBNs. Furthermore, when extracting crisp (i.e., non-probabilistic) predictions from the predicted LBNs, our method outperformed related work on interneuron classification. Our results indicate that our method is adequate for multi-dimensional classification of interneurons with probabilistic labels. Moreover, the introduced morphometric parameters are good predictors of interneuron type and the four features of axonal morphology and thus may serve as objective counterparts to the subjective, categorical axonal features.

Multi-dimensional classification of GABAergic interneurons with Bayesian network-modeled label uncertainty

Interneuron classification is an important and long-debated topic in neuroscience. A recent study provided a data set of digitally reconstructed interneurons classified by 42 leading neuroscientists according to a pragmatic classification scheme composed of five categorical variables, namely, of the interneuron type and four features of axonal morphology. From this data set we now learned a model which can classify interneurons, on the basis of their axonal morphometric parameters, into these five descriptive variables simultaneously. Because of differences in opinion among the neuroscientists, especially regarding neuronal type, for many interneurons we lacked a unique, agreed-upon classification, which we could use to guide model learning. Instead, we guided model learning with a probability distribution over the neuronal type and the axonal features, obtained, for each interneuron, from the neuroscientists’ classification choices. We conveniently encoded such probability distributions with Bayesian networks, calling them label Bayesian networks (LBNs), and developed a method to predict them. This method predicts an LBN by forming a probabilistic consensus among the LBNs of the interneurons most similar to the one being classified. We used 18 axonal morphometric parameters as predictor variables, 13 of which we introduce in this paper as quantitative counterparts to the categorical axonal features. We were able to accurately predict interneuronal LBNs. Furthermore, when extracting crisp (i.e., non-probabilistic) predictions from the predicted LBNs, our method outperformed related work on interneuron classification. Our results indicate that our method is adequate for multi-dimensional classification of interneurons with probabilistic labels. Moreover, the introduced morphometric parameters are good predictors of interneuron type and the four features of axonal morphology and thus may serve as objective counterparts to the subjective, categorical axonal features.

Finding structures in information networks using the affinity network

This thesis proposes a novel graphical model for inference called the Affinity Network,which displays the closeness between pairs of variables and is an alternative to Bayesian Networks and Dependency Networks. The Affinity Network shares some similarities with Bayesian Networks and Dependency Networks but avoids their heuristic and stochastic graph construction algorithms by using a message passing scheme. A comparison with the above two instances of graphical models is given for sparse discrete and continuous medical data and data taken from the UCI machine learning repository. The experimental study reveals that the Affinity Network graphs tend to be more accurate on the basis of an exhaustive search with the small datasets. Moreover, the graph construction algorithm is faster than the other two methods with huge datasets. The Affinity Network is also applied to data produced by a synchronised system. A detailed analysis and numerical investigation into this dynamical system is provided and it is shown that the Affinity Network can be used to characterise its emergent behaviour even in the presence of noise.

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.

Structure learning of context-specific graphical models

Abstract The ultimate problem considered in this thesis is modeling a high-dimensional joint distribution over a set of discrete variables. For this purpose, we consider classes of context-specific graphical models and the main emphasis is on learning the structure of such models from data. Traditional graphical models compactly represent a joint distribution through a factorization justi ed by statements of conditional independence which are encoded by a graph structure. Context-speci c independence is a natural generalization of conditional independence that only holds in a certain context, speci ed by the conditioning variables. We introduce context-speci c generalizations of both Bayesian networks and Markov networks by including statements of context-specific independence which can be encoded as a part of the model structures. For the purpose of learning context-speci c model structures from data, we derive score functions, based on results from Bayesian statistics, by which the plausibility of a structure is assessed. To identify high-scoring structures, we construct stochastic and deterministic search algorithms designed to exploit the structural decomposition of our score functions. Numerical experiments on synthetic and real-world data show that the increased exibility of context-specific structures can more accurately emulate the dependence structure among the variables and thereby improve the predictive accuracy of the models.

Integrated Bayesian network frameworks for modelling complex ecological issues

Ecological problems are typically multi faceted and need to be addressed from a scientific and a management perspective. There is a wealth of modelling and simulation software available, each designed to address a particular aspect of the issue of concern. Choosing the appropriate tool, making sense of the disparate outputs, and taking decisions when little or no empirical data is available, are everyday challenges facing the ecologist and environmental manager. Bayesian Networks provide a statistical modelling framework that enables analysis and integration of information in its own right as well as integration of a variety of models addressing different aspects of a common overall problem. There has been increased interest in the use of BNs to model environmental systems and issues of concern. However, the development of more sophisticated BNs, utilising dynamic and object oriented (OO) features, is still at the frontier of ecological research. Such features are particularly appealing in an ecological context, since the underlying facts are often spatial and temporal in nature. This thesis focuses on an integrated BN approach which facilitates OO modelling. Our research devises a new heuristic method, the Iterative Bayesian Network Development Cycle (IBNDC), for the development of BN models within a multi-field and multi-expert context. Expert elicitation is a popular method used to quantify BNs when data is sparse, but expert knowledge is abundant. The resulting BNs need to be substantiated and validated taking this uncertainty into account. Our research demonstrates the application of the IBNDC approach to support these aspects of BN modelling. The complex nature of environmental issues makes them ideal case studies for the proposed integrated approach to modelling. Moreover, they lend themselves to a series of integrated sub-networks describing different scientific components, combining scientific and management perspectives, or pooling similar contributions developed in different locations by different research groups. In southern Africa the two largest free-ranging cheetah (Acinonyx jubatus) populations are in Namibia and Botswana, where the majority of cheetahs are located outside protected areas. Consequently, cheetah conservation in these two countries is focussed primarily on the free-ranging populations as well as the mitigation of conflict between humans and cheetahs. In contrast, in neighbouring South Africa, the majority of cheetahs are found in fenced reserves. Nonetheless, conflict between humans and cheetahs remains an issue here. Conservation effort in South Africa is also focussed on managing the geographically isolated cheetah populations as one large meta-population. Relocation is one option among a suite of tools used to resolve human-cheetah conflict in southern Africa. Successfully relocating captured problem cheetahs, and maintaining a viable free-ranging cheetah population, are two environmental issues in cheetah conservation forming the first case study in this thesis. The second case study involves the initiation of blooms of Lyngbya majuscula, a blue-green algae, in Deception Bay, Australia. L. majuscula is a toxic algal bloom which has severe health, ecological and economic impacts on the community located in the vicinity of this algal bloom. Deception Bay is an important tourist destination with its proximity to Brisbane, Australia’s third largest city. Lyngbya is one of several algae considered to be a Harmful Algal Bloom (HAB). This group of algae includes other widespread blooms such as red tides. The occurrence of Lyngbya blooms is not a local phenomenon, but blooms of this toxic weed occur in coastal waters worldwide. With the increase in frequency and extent of these HAB blooms, it is important to gain a better understanding of the underlying factors contributing to the initiation and sustenance of these blooms. This knowledge will contribute to better management practices and the identification of those management actions which could prevent or diminish the severity of these blooms.