Training with noise is equivalent to Tikhonov regularization

It is well known that the addition of noise to the input data of a neural network during training can, in some circumstances, lead to significant improvements in generalization performance. Previous work has shown that such training with noise is equivalent to a form of regularization in which an extra term is added to the error function. However, the regularization term, which involves second derivatives of the error function, is not bounded below, and so can lead to difficulties if used directly in a learning algorithm based on error minimization. In this paper we show that, for the purposes of network training, the regularization term can be reduced to a positive definite form which involves only first derivatives of the network mapping. For a sum-of-squares error function, the regularization term belongs to the class of generalized Tikhonov regularizers. Direct minimization of the regularized error function provides a practical alternative to training with noise.

Bayesian regression filter and the issue of priors

We propose a Bayesian framework for regression problems, which covers areas which are usually dealt with by function approximation. An online learning algorithm is derived which solves regression problems with a Kalman filter. Its solution always improves with increasing model complexity, without the risk of over-fitting. In the infinite dimension limit it approaches the true Bayesian posterior. The issues of prior selection and over-fitting are also discussed, showing that some of the commonly held beliefs are misleading. The practical implementation is summarised. Simulations using 13 popular publicly available data sets are used to demonstrate the method and highlight important issues concerning the choice of priors.

Gaussian processes:iterative sparse approximations

In recent years there has been an increased interest in applying non-parametric methods to real-world problems. Significant research has been devoted to Gaussian processes (GPs) due to their increased flexibility when compared with parametric models. These methods use Bayesian learning, which generally leads to analytically intractable posteriors. This thesis proposes a two-step solution to construct a probabilistic approximation to the posterior. In the first step we adapt the Bayesian online learning to GPs: the final approximation to the posterior is the result of propagating the first and second moments of intermediate posteriors obtained by combining a new example with the previous approximation. The propagation of em functional forms is solved by showing the existence of a parametrisation to posterior moments that uses combinations of the kernel function at the training points, transforming the Bayesian online learning of functions into a parametric formulation. The drawback is the prohibitive quadratic scaling of the number of parameters with the size of the data, making the method inapplicable to large datasets. The second step solves the problem of the exploding parameter size and makes GPs applicable to arbitrarily large datasets. The approximation is based on a measure of distance between two GPs, the KL-divergence between GPs. This second approximation is with a constrained GP in which only a small subset of the whole training dataset is used to represent the GP. This subset is called the em Basis Vector, or BV set and the resulting GP is a sparse approximation to the true posterior. As this sparsity is based on the KL-minimisation, it is probabilistic and independent of the way the posterior approximation from the first step is obtained. We combine the sparse approximation with an extension to the Bayesian online algorithm that allows multiple iterations for each input and thus approximating a batch solution. The resulting sparse learning algorithm is a generic one: for different problems we only change the likelihood. The algorithm is applied to a variety of problems and we examine its performance both on more classical regression and classification tasks and to the data-assimilation and a simple density estimation problems.

Critical success factors for IS executive careers

This article qualitatively analyzes the Critical Success Factors (CSFs) for Information Systems (IS) executive careers based on evidence gathered from five case studies carried out in 1997. Typical IS executive career paths are presented within a time series style and the CSFs are interpreted within a descriptive framework by synthesising the case data based on Social Cognitive Theory. The descriptive framework suggests that successful IS executive careers would most likely be achieved by well educated and experienced IS employees who have the right attitude towards both their career and work, together with good performance. They would also exhibit an ability for self-learning and to anticipate future IT uses, as well as having proficient IS management knowledge and skills while working with an appropriate organizational environment. Moreover, the framework systematically indicates the interactions between the coupling factors in the typical career development processes. This provides a benchmark for employees that are aiming at a senior IS executive career against which they can compare their own achievements and aspirations. It also raises propositions for further research on theory building.

Neural networks for perpetual grouping

A number of researchers have investigated the application of neural networks to visual recognition, with much of the emphasis placed on exploiting the network's ability to generalise. However, despite the benefits of such an approach it is not at all obvious how networks can be developed which are capable of recognising objects subject to changes in rotation, translation and viewpoint. In this study, we suggest that a possible solution to this problem can be found by studying aspects of visual psychology and in particular, perceptual organisation. For example, it appears that grouping together lines based upon perceptually significant features can facilitate viewpoint independent recognition. The work presented here identifies simple grouping measures based on parallelism and connectivity and shows how it is possible to train multi-layer perceptrons (MLPs) to detect and determine the perceptual significance of any group presented. In this way, it is shown how MLPs which are trained via backpropagation to perform individual grouping tasks, can be brought together into a novel, large scale network capable of determining the perceptual significance of the whole input pattern. Finally the applicability of such significance values for recognition is investigated and results indicate that both the NILP and the Kohonen Feature Map can be trained to recognise simple shapes described in terms of perceptual significances. This study has also provided an opportunity to investigate aspects of the backpropagation algorithm, particularly the ability to generalise. In this study we report the results of various generalisation tests. In applying the backpropagation algorithm to certain problems, we found that there was a deficiency in performance with the standard learning algorithm. An improvement in performance could however, be obtained when suitable modifications were made to the algorithm. The modifications and consequent results are reported here.

Can a student learn optimally from two different teachers

We explore the effects of over-specificity in learning algorithms by investigating the behavior of a student, suited to learn optimally from a teacher B, learning from a teacher B' ? B. We only considered the supervised, on-line learning scenario with teachers selected from a particular family. We found that, in the general case, the application of the optimal algorithm to the wrong teacher produces a residual generalization error, even if the right teacher is harder. By imposing mild conditions to the learning algorithm form, we obtained an approximation for the residual generalization error. Simulations carried out in finite networks validate the estimate found.

Stock selection with full-scale optimization and differential evolution

When composing stock portfolios, managers frequently choose among hundreds of stocks. The stocks' risk properties are analyzed with statistical tools, and managers try to combine these to meet the investors' risk profiles. A recently developed tool for performing such optimization is called full-scale optimization (FSO). This methodology is very flexible for investor preferences, but because of computational limitations it has until now been infeasible to use when many stocks are considered. We apply the artificial intelligence technique of differential evolution to solve FSO-type stock selection problems of 97 assets. Differential evolution finds the optimal solutions by self-learning from randomly drawn candidate solutions. We show that this search technique makes large scale problem computationally feasible and that the solutions retrieved are stable. The study also gives further merit to the FSO technique, as it shows that the solutions suit investor risk profiles better than portfolios retrieved from traditional methods.

Mining web data for competency management

We present CORDER (COmmunity Relation Discovery by named Entity Recognition) an un-supervised machine learning algorithm that exploits named entity recognition and co-occurrence data to associate individuals in an organization with their expertise and associates. We discuss the problems associated with evaluating unsupervised learners and report our initial evaluation experiments.

General Regression Neuro–Fuzzy Network for Identification of Nonstationary Plants

General Regression Neuro-Fuzzy Network, which combines the properties of conventional General Regression Neural Network and Adaptive Network-based Fuzzy Inference System is proposed in this work. This network relates to so-called “memory-based networks”, which is adjusted by one-pass learning algorithm.

Experiments with two Approaches for Tracking Drifting Concepts

This paper addresses the task of learning classifiers from streams of labelled data. In this case we can face the problem that the underlying concepts can change over time. The paper studies two mechanisms developed for dealing with changing concepts. Both are based on the time window idea. The first one forgets gradually, by assigning to the examples weight that gradually decreases over time. The second one uses a statistical test to detect changes in concept and then optimizes the size of the time window, aiming to maximise the classification accuracy on the new examples. Both methods are general in nature and can be used with any learning algorithm. The objectives of the conducted experiments were to compare the mechanisms and explore whether they can be combined to achieve a synergetic e ect. Results from experiments with three basic learning algorithms (kNN, ID3 and NBC) using four datasets are reported and discussed.

Double-Wavelet Neuron Based on Analytical Activation Functions

In this paper a new double-wavelet neuron architecture obtained by modification of standard wavelet neuron, and its learning algorithm are proposed. The offered architecture allows to improve the approximation properties of wavelet neuron. Double-wavelet neuron and its learning algorithm are examined for forecasting non-stationary chaotic time series.

Data Mining for Browsing Patterns in Weblog Data by Art Neural Networks

Categorising visitors based on their interaction with a website is a key problem in Web content usage. The clickstreams generated by various users often follow distinct patterns, the knowledge of which may help in providing customised content. This paper proposes an approach to clustering weblog data, based on ART2 neural networks. Due to the characteristics of the ART2 neural network model, the proposed approach can be used for unsupervised and self-learning data mining, which makes it adaptable to dynamically changing websites.

Development, Annotation and Protection of Digital Archive “Bulgarian Folklore Heritage”

The key to prosperity in today's world is access to digital content and skills to create new content. Investigations of folklore artifacts is the topic of this article, presenting research related to the national program „Knowledge Technologies for Creation of Digital Presentation and Significant Repositories of Folklore Heritage” (FolkKnow). FolkKnow aims to build a digital multimedia archive "Bulgarian Folklore Heritage” (BFH) and virtual information portal with folk media library of digitized multimedia objects from a selected collection of the fund of Institute of Ethnology and Folklore Studies with Ethnographic Museum (IEFSEM) of the Bulgarian Academy of Science (BAS). The realization of the project FolkKnow gives opportunity for wide social applications of the multimedia collections, for the purposes of Interactive distance learning/self-learning, research activities in the field of Bulgarian traditional culture and for the cultural and ethno-tourism. We study, analyze and implement techniques and methods for digitization of multimedia objects and their annotation. In the paper are discussed specifics approaches used to building and protect a digital archive with multimedia content. Tasks can be systematized in the following guidelines: * Digitization of the selected samples * Analysis of the objects in order to determine the metadata of selected artifacts from selected collections and problem areas * Digital multimedia archive * Socially-oriented applications and virtual exhibitions artery * Frequency dictionary tool for texts with folklore themes * A method of modern technologies of protecting intellectual property and copyrights on digital content developed for use in digital exposures.

A Stochastic Approach for Finding of Semantically Related Words

2000 Mathematics Subject Classification: 62P99, 68T50

A multimedia indexing and retrieval framework for multimedia database systems

The main challenges of multimedia data retrieval lie in the effective mapping between low-level features and high-level concepts, and in the individual users' subjective perceptions of multimedia content. ^ The objectives of this dissertation are to develop an integrated multimedia indexing and retrieval framework with the aim to bridge the gap between semantic concepts and low-level features. To achieve this goal, a set of core techniques have been developed, including image segmentation, content-based image retrieval, object tracking, video indexing, and video event detection. These core techniques are integrated in a systematic way to enable the semantic search for images/videos, and can be tailored to solve the problems in other multimedia related domains. In image retrieval, two new methods of bridging the semantic gap are proposed: (1) for general content-based image retrieval, a stochastic mechanism is utilized to enable the long-term learning of high-level concepts from a set of training data, such as user access frequencies and access patterns of images. (2) In addition to whole-image retrieval, a novel multiple instance learning framework is proposed for object-based image retrieval, by which a user is allowed to more effectively search for images that contain multiple objects of interest. An enhanced image segmentation algorithm is developed to extract the object information from images. This segmentation algorithm is further used in video indexing and retrieval, by which a robust video shot/scene segmentation method is developed based on low-level visual feature comparison, object tracking, and audio analysis. Based on shot boundaries, a novel data mining framework is further proposed to detect events in soccer videos, while fully utilizing the multi-modality features and object information obtained through video shot/scene detection. ^ Another contribution of this dissertation is the potential of the above techniques to be tailored and applied to other multimedia applications. This is demonstrated by their utilization in traffic video surveillance applications. The enhanced image segmentation algorithm, coupled with an adaptive background learning algorithm, improves the performance of vehicle identification. A sophisticated object tracking algorithm is proposed to track individual vehicles, while the spatial and temporal relationships of vehicle objects are modeled by an abstract semantic model. ^