Hierarchical Mixtures of Experts and the EM Algorithm

We present a tree-structured architecture for supervised learning. The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coefficients and the mixture components are generalized linear models (GLIM's). Learning is treated as a maximum likelihood problem; in particular, we present an Expectation-Maximization (EM) algorithm for adjusting the parameters of the architecture. We also develop an on-line learning algorithm in which the parameters are updated incrementally. Comparative simulation results are presented in the robot dynamics domain.

Hierarchical Prediction Machines and Big Data Analytics

An emerging consensus in cognitive science views the biological brain as a hierarchically-organized predictive processing system. This is a system in which higher-order regions are continuously attempting to predict the activity of lower-order regions at a variety of (increasingly abstract) spatial and temporal scales. The brain is thus revealed as a hierarchical prediction machine that is constantly engaged in the effort to predict the flow of information originating from the sensory surfaces. Such a view seems to afford a great deal of explanatory leverage when it comes to a broad swathe of seemingly disparate psychological phenomena (e.g., learning, memory, perception, action, emotion, planning, reason, imagination, and conscious experience). In the most positive case, the predictive processing story seems to provide our first glimpse at what a unified (computationally-tractable and neurobiological plausible) account of human psychology might look like. This obviously marks out one reason why such models should be the focus of current empirical and theoretical attention. Another reason, however, is rooted in the potential of such models to advance the current state-of-the-art in machine intelligence and machine learning. Interestingly, the vision of the brain as a hierarchical prediction machine is one that establishes contact with work that goes under the heading of 'deep learning'. Deep learning systems thus often attempt to make use of predictive processing schemes and (increasingly abstract) generative models as a means of supporting the analysis of large data sets. But are such computational systems sufficient (by themselves) to provide a route to general human-level analytic capabilities? I will argue that they are not and that closer attention to a broader range of forces and factors (many of which are not confined to the neural realm) may be required to understand what it is that gives human cognition its distinctive (and largely unique) flavour. The vision that emerges is one of 'homomimetic deep learning systems', systems that situate a hierarchically-organized predictive processing core within a larger nexus of developmental, behavioural, symbolic, technological and social influences. Relative to that vision, I suggest that we should see the Web as a form of 'cognitive ecology', one that is as much involved with the transformation of machine intelligence as it is with the progressive reshaping of our own cognitive capabilities.

The seasonal forecast of electricity demand: A hierarchical Bayesian model with climatological weather generator

In this paper we focus on the one year ahead prediction of the electricity peak-demand daily trajectory during the winter season in Central England and Wales. We define a Bayesian hierarchical model for predicting the winter trajectories and present results based on the past observed weather. Thanks to the flexibility of the Bayesian approach, we are able to produce the marginal posterior distributions of all the predictands of interest. This is a fundamental progress with respect to the classical methods. The results are encouraging in both skill and representation of uncertainty. Further extensions are straightforward at least in principle. The main two of those consist in conditioning the weather generator model with respect to additional information like the knowledge of the first part of the winter and/or the seasonal weather forecast. Copyright (C) 2006 John Wiley & Sons, Ltd.

A hierarchical Bayesian model for predicting the functional consequences of amino-acid polymorphisms

Genetic polymorphisms in deoxyribonucleic acid coding regions may have a phenotypic effect on the carrier, e.g. by influencing susceptibility to disease. Detection of deleterious mutations via association studies is hampered by the large number of candidate sites; therefore methods are needed to narrow down the search to the most promising sites. For this, a possible approach is to use structural and sequence-based information of the encoded protein to predict whether a mutation at a particular site is likely to disrupt the functionality of the protein itself. We propose a hierarchical Bayesian multivariate adaptive regression spline (BMARS) model for supervised learning in this context and assess its predictive performance by using data from mutagenesis experiments on lac repressor and lysozyme proteins. In these experiments, about 12 amino-acid substitutions were performed at each native amino-acid position and the effect on protein functionality was assessed. The training data thus consist of repeated observations at each position, which the hierarchical framework is needed to account for. The model is trained on the lac repressor data and tested on the lysozyme mutations and vice versa. In particular, we show that the hierarchical BMARS model, by allowing for the clustered nature of the data, yields lower out-of-sample misclassification rates compared with both a BMARS and a frequen-tist MARS model, a support vector machine classifier and an optimally pruned classification tree.

The seasonal forecast of electricity demand: A hierarchical Bayesian model with climatological weather generator

In this paper we focus on the one year ahead prediction of the electricity peak-demand daily trajectory during the winter season in Central England and Wales. We define a Bayesian hierarchical model for predicting the winter trajectories and present results based on the past observed weather. Thanks to the flexibility of the Bayesian approach, we are able to produce the marginal posterior distributions of all the predictands of interest. This is a fundamental progress with respect to the classical methods. The results are encouraging in both skill and representation of uncertainty. Further extensions are straightforward at least in principle. The main two of those consist in conditioning the weather generator model with respect to additional information like the knowledge of the first part of the winter and/or the seasonal weather forecast. Copyright (C) 2006 John Wiley & Sons, Ltd.

Improvement of classification accuracy for stochastic discrimination - Multi-class classification

In this paper, an improved stochastic discrimination (SD) is introduced to reduce the error rate of the standard SD in the context of multi-class classification problem. The learning procedure of the improved SD consists of two stages. In the first stage, a standard SD, but with shorter learning period is carried out to identify an important space where all the misclassified samples are located. In the second stage, the standard SD is modified by (i) restricting sampling in the important space; and (ii) introducing a new discriminant function for samples in the important space. It is shown by mathematical derivation that the new discriminant function has the same mean, but smaller variance than that of standard SD for samples in the important space. It is also analyzed that the smaller the variance of the discriminant function, the lower the error rate of the classifier. Consequently, the proposed improved SD improves standard SD by its capability of achieving higher classification accuracy. Illustrative examples axe provided to demonstrate the effectiveness of the proposed improved SD.

On improvement of classification accuracy for stochastic discrimination

Stochastic discrimination (SD) depends on a discriminant function for classification. In this paper, an improved SD is introduced to reduce the error rate of the standard SD in the context of a two-class classification problem. The learning procedure of the improved SD consists of two stages. Initially a standard SD, but with shorter learning period is carried out to identify an important space where all the misclassified samples are located. Then the standard SD is modified by 1) restricting sampling in the important space, and 2) introducing a new discriminant function for samples in the important space. It is shown by mathematical derivation that the new discriminant function has the same mean, but with a smaller variance than that of the standard SD for samples in the important space. It is also analyzed that the smaller the variance of the discriminant function, the lower the error rate of the classifier. Consequently, the proposed improved SD improves standard SD by its capability of achieving higher classification accuracy. Illustrative examples are provided to demonstrate the effectiveness of the proposed improved SD.

Direct Computation of Stochastic Flow in Reservoirs with Uncertain Parameters

A direct method is presented for determining the uncertainty in reservoir pressure, flow, and net present value (NPV) using the time-dependent, one phase, two- or three-dimensional equations of flow through a porous medium. The uncertainty in the solution is modelled as a probability distribution function and is computed from given statistical data for input parameters such as permeability. The method generates an expansion for the mean of the pressure about a deterministic solution to the system equations using a perturbation to the mean of the input parameters. Hierarchical equations that define approximations to the mean solution at each point and to the field covariance of the pressure are developed and solved numerically. The procedure is then used to find the statistics of the flow and the risked value of the field, defined by the NPV, for a given development scenario. This method involves only one (albeit complicated) solution of the equations and contrasts with the more usual Monte-Carlo approach where many such solutions are required. The procedure is applied easily to other physical systems modelled by linear or nonlinear partial differential equations with uncertain data.

Learning to lead for business growth – implications for supporting SMEs in Wales

The Welsh private and third sectors are heavily dependent on SMEs. Consequently the performance of SMEs is critical to the performance of the Welsh economy. Substantial public funds, particularly from European Structural Funds, have been allocated to support these since 2000. The majority of programmes thus funded have been led from within the Welsh Government. This paper reports interim evaluation findings from one intervention led by two Welsh higher education institutions (HEIs), namely the LEAD Wales programme. The programme is an extended intervention to support the leadership skills of owner-managers and incorporates a range of learning methods, including formal masterclasses, but emphasizes situated and experiential learning through action learning, coaching and peer-to-peer exchange exercises. The programme’s impact is assessed on the experiences of 325 participants, of whom 217 have completed the programme. The paper concludes that situated learning methods, through which participants are able to draw from shared history and experience over an extended period are critical to programme success. By contrast, short-term thematic teaching, based around more formal, hierarchical learning is less likely to yield significant and sustainable economic benefits. The implications of this for business support in Wales are discussed.

HIERARCHICAL DECOMPOSITION OF MULTICLASS PROBLEMS

Several popular Machine Learning techniques are originally designed for the solution of two-class problems. However, several classification problems have more than two classes. One approach to deal with multiclass problems using binary classifiers is to decompose the multiclass problem into multiple binary sub-problems disposed in a binary tree. This approach requires a binary partition of the classes for each node of the tree, which defines the tree structure. This paper presents two algorithms to determine the tree structure taking into account information collected from the used dataset. This approach allows the tree structure to be determined automatically for any multiclass dataset.

The application of a reinforcement learning agent to a multi-product manufacturing facility

An intelligent agent-based scheduling system, consisting of a reinforcement learning agent and a simulation model has been developed and tested on a classic scheduling problem. The production facility studied is a multiproduct serial line subject to stochastic failure. The agent goal is to minimise total production costs, through selection of job sequence and batch size. To explore state space the agent used reinforcement learning. By applying an independent inventory control policy for each product, the agent successfully identified optimal operating policies for a real production facility.

An introduction to eRoadmapping : providing learning paths for students and empowering teachers

This paper reports on the development of an innovative teaching strategy: an eRoadmap.  Based on the theory of conceptual mapping, the eRoadmap provides an interactive, hierarchical structure for course delivery, using the readily accessible platform provided by Microsoft PowerPoint.  For the student, the eRoadmap provides a self-paced learning environment which encourages student engagement; for the teacher, it provides an environment for the development of a course framework, and the integration of teaching materials from a variety of sources.  Futher advantages of the eRoadmap from the perspectives of both students and teachers are discussed, and future directions for development, evaluation and research are outlined.

Learning to detect texture objects by artificial immune approaches

This paper introduces a novel method to detect texture objects from satellite images. First, a hierarchical strategy is developed to extract texture objects according to their roughness. Then, an artificial immune approach is presented to automatically generate segmentation thresholds and texture filters, which are used in the hierarchical strategy. In this approach, texture objects are regarded as antigens, and texture object filters and segmentation thresholds are regarded as antibodies. The clonal selection algorithm inspired by human immune system is employed to evolve antibodies. The population of antibodies is iteratively evaluated according to a statistical performance index corresponding to object detection ability, and evolves into the optimal antibody using the evolution principles of the clonal selection. Experimental results of texture object detection on satellite images are presented to illustrate the merit and feasibility of the proposed method.

Optimising discrete event simulation models using a reinforcement learning agent

A reinforcement learning agent has been developed to determine optimal operating policies in a multi-part serial line. The agent interacts with a discrete event simulation model of a stochastic production facility. This study identifies issues important to the simulation developer who wishes to optimise a complex simulation or develop a robust operating policy. Critical parameters pertinent to 'tuning' an agent quickly and enabling it to rapidly learn the system were investigated.