Can diversity amongst learners improve online object tracking?

We present a novel analysis of the state of the art in object tracking with respect to diversity found in its main component, an ensemble classifier that is updated in an online manner. We employ established measures for diversity and performance from the rich literature on ensemble classification and online learning, and present a detailed evaluation of diversity and performance on benchmark sequences in order to gain an insight into how the tracking performance can be improved. © Springer-Verlag 2013.

Learning user and product distributed representations using a sequence model for sentiment analysis

In product reviews, it is observed that the distribution of polarity ratings over reviews written by different users or evaluated based on different products are often skewed in the real world. As such, incorporating user and product information would be helpful for the task of sentiment classification of reviews. However, existing approaches ignored the temporal nature of reviews posted by the same user or evaluated on the same product. We argue that the temporal relations of reviews might be potentially useful for learning user and product embedding and thus propose employing a sequence model to embed these temporal relations into user and product representations so as to improve the performance of document-level sentiment analysis. Specifically, we first learn a distributed representation of each review by a one-dimensional convolutional neural network. Then, taking these representations as pretrained vectors, we use a recurrent neural network with gated recurrent units to learn distributed representations of users and products. Finally, we feed the user, product and review representations into a machine learning classifier for sentiment classification. Our approach has been evaluated on three large-scale review datasets from the IMDB and Yelp. Experimental results show that: (1) sequence modeling for the purposes of distributed user and product representation learning can improve the performance of document-level sentiment classification; (2) the proposed approach achieves state-of-The-Art results on these benchmark datasets.

CLAE to move to online format

Editorial: The 2015 BCLA annual conference was another fantastic affair. It was the first time the conference was held in the beautiful city of Liverpool. The venue was great and the programme was excellent. The venue overlooked the River Mersey and many of the hotels were local boutique hotels. I stayed in one which was formerly the offices of White Star Liners—where the RMS Titanic was originally registered. The hotel decor was consistent with its historic significance. The BCLA gala dinner was held in the hugely impressive Anglican Cathedral with entertainment from a Beatles tribute band. That will certainly be a hard act to follow at the next conference in 2017. Brian Tompkins took the reigns as the new BCLA president. Professor Fiona Stapleton was the recipient of the BCLA Gold Medal Award. The winner of the poster competition was Dorota Szczesna-Iskander with a poster entitled ‘Dry Contact lens poor wettability and visual performance’. Second place was Renee Reeder with her poster entitled ‘Abnormal Rosacea as a differential diagnosis in corneal scarring’. And third place was Maria Jesus Gonzalez-Garcia with her poster entitled ‘Dry Effect of the Environmental Conditions on Tear Inflammatory Mediators Concentration in Contact Lens Wearers’. The photographic competition winner was Professor Wolfgang Sickenberger from Jena in Germany. The Editorial Panel of CLAE met at the BCLA conference for their first biannual meeting. The journal metrics were discussed. In terms of number of submissions of new papers CLAE seems to have plateaued after seeing a rapid growth in the number of submissions over the last few years. The increase over the last few years could be attributed to the fact that CLAE was awarded an impact factor for the first time in 2012. This year it seems that impact factors across nearly all ophthalmic related journals has dropped. This could in part be due to the fact that last year was a ‘Research Exercise Framework (REF) year for UK universities, where they are judged on quality of their research output. The next REF is in 2020 so we may see changes nearing that time. Looking at article downloads, there seems to be a continued rise in figures. Currently CLAE attracts around 85,000 downloads per year (this is an increase of around 10,000 per year for the last few years) and the 2015 prediction is 120,000! With this in mind and with other contributing factors too, the BCLA has decided to move to online delivery of CLAE to its members starting from issue 5 of 2015. Some members do like to flick through the pages of a hard copy of the journal so members will still have the option of receiving a hard copy through the post but the default journal delivery method will now be online. The BCLA office will send various alerts and content details to members email addresses. To access CLAE online you will need to log in via the BCLA web page, currently you then click on ‘Resources’ and then under ‘Free and Discounted Publications’ you will see CLAE. This actually takes you to CLAE’s own webpage (www.contactlensjournal.com) but you need to log in via the BCLA web page. The BCLA plans to change these weblinks so that from the BCLA web page you can link to the journal website much more easily and you have the choice of going directly into the general website for CLAE or straight to the current issue. In 2016 you will see an even easier way of accessing CLAE online as the BCLA will launch a CLAE application for mobile devices where the journal can be downloaded as a ‘flick-book’. This is a great way of bringing CLAE into the modern era where people access their information in newer ways. For many the BCLA conference was part of a very busy conference week as it was preceded by the International Association of Contact Lens Educators’ (IACLE) Third World Congress, held in Manchester on the 4 days before the BCLA conference. The first and second IACE World Congresses were held in Waterloo, Canada in 1994 and 2000 respectively and hosted by Professor Des Fonn. Professor Fonn was the recipient of the first ever IACLE lifetime achievement award. The Third IACLE World Congress saw more than 100 contact lens educators and industry representatives from around 30 countries gather in the UK for the four-day event, hosted by The University of Manchester. Delegates gained hands-on experience of innovations in teaching, such as learning delivery systems, the use of iPads in the classroom and for creating ePub content, and augmented and virtual reality technologies. IACLE members around the world also took part via a live online broadcast. The Third IACLE World Congress was made possible by the generous support of Sponsors Alcon, CooperVision and Johnson & Johnson Vision Care., for more information look at the IACLE web page (www.iacle.org).

Probabilistic topographic information visualisation

The focus of this thesis is the extension of topographic visualisation mappings to allow for the incorporation of uncertainty. Few visualisation algorithms in the literature are capable of mapping uncertain data with fewer able to represent observation uncertainties in visualisations. As such, modifications are made to NeuroScale, Locally Linear Embedding, Isomap and Laplacian Eigenmaps to incorporate uncertainty in the observation and visualisation spaces. The proposed mappings are then called Normally-distributed NeuroScale (N-NS), T-distributed NeuroScale (T-NS), Probabilistic LLE (PLLE), Probabilistic Isomap (PIso) and Probabilistic Weighted Neighbourhood Mapping (PWNM). These algorithms generate a probabilistic visualisation space with each latent visualised point transformed to a multivariate Gaussian or T-distribution, using a feed-forward RBF network. Two types of uncertainty are then characterised dependent on the data and mapping procedure. Data dependent uncertainty is the inherent observation uncertainty. Whereas, mapping uncertainty is defined by the Fisher Information of a visualised distribution. This indicates how well the data has been interpolated, offering a level of ‘surprise’ for each observation. These new probabilistic mappings are tested on three datasets of vectorial observations and three datasets of real world time series observations for anomaly detection. In order to visualise the time series data, a method for analysing observed signals and noise distributions, Residual Modelling, is introduced. The performance of the new algorithms on the tested datasets is compared qualitatively with the latent space generated by the Gaussian Process Latent Variable Model (GPLVM). A quantitative comparison using existing evaluation measures from the literature allows performance of each mapping function to be compared. Finally, the mapping uncertainty measure is combined with NeuroScale to build a deep learning classifier, the Cascading RBF. This new structure is tested on the MNist dataset achieving world record performance whilst avoiding the flaws seen in other Deep Learning Machines.

Organisational learning - a critical systems thinking discipline

Original Paper European Journal of Information Systems (2001) 10, 135–146; doi:10.1057/palgrave.ejis.3000394 Organisational learning—a critical systems thinking discipline P Panagiotidis1,3 and J S Edwards2,4 1Deloitte and Touche, Athens, Greece 2Aston Business School, Aston University, Aston Triangle, Birmingham, B4 7ET, UK Correspondence: Dr J S Edwards, Aston Business School, Aston University, Aston Triangle, Birmingham, B4 7ET, UK. E-mail: j.s.edwards@aston.ac.uk 3Petros Panagiotidis is Manager responsible for the Process and Systems Integrity Services of Deloitte and Touche in Athens, Greece. He has a BSc in Business Administration and an MSc in Management Information Systems from Western International University, Phoenix, Arizona, USA; an MSc in Business Systems Analysis and Design from City University, London, UK; and a PhD degree from Aston University, Birmingham, UK. His doctorate was in Business Systems Analysis and Design. His principal interests now are in the ERP/DSS field, where he serves as project leader and project risk managment leader in the implementation of SAP and JD Edwards/Cognos in various major clients in the telecommunications and manufacturing sectors. In addition, he is responsible for the development and application of knowledge management systems and activity-based costing systems. 4John S Edwards is Senior Lecturer in Operational Research and Systems at Aston Business School, Birmingham, UK. He holds MA and PhD degrees (in mathematics and operational research respectively) from Cambridge University. His principal research interests are in knowledge management and decision support, especially methods and processes for system development. He has written more than 30 research papers on these topics, and two books, Building Knowledge-based Systems and Decision Making with Computers, both published by Pitman. Current research work includes the effect of scale of operations on knowledge management, interfacing expert systems with simulation models, process modelling in law and legal services, and a study of the use of artifical intelligence techniques in management accounting. Top of pageAbstract This paper deals with the application of critical systems thinking in the domain of organisational learning and knowledge management. Its viewpoint is that deep organisational learning only takes place when the business systems' stakeholders reflect on their actions and thus inquire about their purpose(s) in relation to the business system and the other stakeholders they perceive to exist. This is done by reflecting both on the sources of motivation and/or deception that are contained in their purpose, and also on the sources of collective motivation and/or deception that are contained in the business system's purpose. The development of an organisational information system that captures, manages and institutionalises meaningful information—a knowledge management system—cannot be separated from organisational learning practices, since it should be the result of these very practices. Although Senge's five disciplines provide a useful starting-point in looking at organisational learning, we argue for a critical systems approach, instead of an uncritical Systems Dynamics one that concentrates only on the organisational learning practices. We proceed to outline a methodology called Business Systems Purpose Analysis (BSPA) that offers a participatory structure for team and organisational learning, upon which the stakeholders can take legitimate action that is based on the force of the better argument. In addition, the organisational learning process in BSPA leads to the development of an intrinsically motivated information organisational system that allows for the institutionalisation of the learning process itself in the form of an organisational knowledge management system. This could be a specific application, or something as wide-ranging as an Enterprise Resource Planning (ERP) implementation. Examples of the use of BSPA in two ERP implementations are presented.

Supplementing the virtual learning environment for information systems graduate education

DUE TO COPYRIGHT RESTRICTIONS ONLY AVAILABLE FOR CONSULTATION AT ASTON UNIVERSITY LIBRARY AND INFORMATION SERVICES WITH PRIOR ARRANGEMENT

Looking under the bonnet:factors affecting student adoption of e-learning systems in Jordan

The primary questions addressed in this paper are the following: what are the factors that affect students’ adoption of an e-learning system and what are the relationships among these factors? This paper investigates and identifies some of the major factors affecting students’ adoption of an e-learning system in a university in Jordan. E-learning adoption is approached from the information systems acceptance point of view. This suggests that a prior condition for learning effectively using e-learning systems is that students must actually use them. Thus, a greater knowledge of the factors that affect IT adoption and their interrelationships is a pre-cursor to a better understanding of student acceptance of e-learning systems. In turn, this will help and guide those who develop, implement, and deliver e-learning systems. In this study, an extended version of the Technology Acceptance Model (TAM) was developed to investigate the underlying factors that influence students’ decisions to use an e-learning system. The TAM was populated using data gathered from a survey of 486 undergraduate students using the Moodle based e-learning system at the Arab Open University. The model was estimated using Structural Equation Modelling (SEM). A path model was developed to analyze the relationships between the factors to explain students’ adoption of the e-learning system. Whilst findings support existing literature about prior experience affecting perceptions, they also point to surprising group effects, which may merit future exploration.

The evolution of learning systems:to Bayes or not to be

Bayesian algorithms pose a limit to the performance learning algorithms can achieve. Natural selection should guide the evolution of information processing systems towards those limits. What can we learn from this evolution and what properties do the intermediate stages have? While this question is too general to permit any answer, progress can be made by restricting the class of information processing systems under study. We present analytical and numerical results for the evolution of on-line algorithms for learning from examples for neural network classifiers, which might include or not a hidden layer. The analytical results are obtained by solving a variational problem to determine the learning algorithm that leads to maximum generalization ability. Simulations using evolutionary programming, for programs that implement learning algorithms, confirm and expand the results. The principal result is not just that the evolution is towards a Bayesian limit. Indeed it is essentially reached. In addition we find that evolution is driven by the discovery of useful structures or combinations of variables and operators. In different runs the temporal order of the discovery of such combinations is unique. The main result is that combinations that signal the surprise brought by an example arise always before combinations that serve to gauge the performance of the learning algorithm. This latter structures can be used to implement annealing schedules. The temporal ordering can be understood analytically as well by doing the functional optimization in restricted functional spaces. We also show that there is data suggesting that the appearance of these traits also follows the same temporal ordering in biological systems. © 2006 American Institute of Physics.

User-centred ontology learning for knowledge management

Automatic ontology building is a vital issue in many fields where they are currently built manually. This paper presents a user-centred methodology for ontology construction based on the use of Machine Learning and Natural Language Processing. In our approach, the user selects a corpus of texts and sketches a preliminary ontology (or selects an existing one) for a domain with a preliminary vocabulary associated to the elements in the ontology (lexicalisations). Examples of sentences involving such lexicalisation (e.g. ISA relation) in the corpus are automatically retrieved by the system. Retrieved examples are validated by the user and used by an adaptive Information Extraction system to generate patterns that discover other lexicalisations of the same objects in the ontology, possibly identifying new concepts or relations. New instances are added to the existing ontology or used to tune it. This process is repeated until a satisfactory ontology is obtained. The methodology largely automates the ontology construction process and the output is an ontology with an associated trained leaner to be used for further ontology modifications.

Curvature-driven smoothing: a learning algorithm for feed-forward networks

The performance of feed-forward neural networks in real applications can be often be improved significantly if use is made of a-priori information. For interpolation problems this prior knowledge frequently includes smoothness requirements on the network mapping, and can be imposed by the addition to the error function of suitable regularization terms. The new error function, however, now depends on the derivatives of the network mapping, and so the standard back-propagation algorithm cannot be applied. In this paper, we derive a computationally efficient learning algorithm, for a feed-forward network of arbitrary topology, which can be used to minimize the new error function. Networks having a single hidden layer, for which the learning algorithm simplifies, are treated as a special case.

Time trials on second-order and variable-learning-rate algorithms

The performance of seven minimization algorithms are compared on five neural network problems. These include a variable-step-size algorithm, conjugate gradient, and several methods with explicit analytic or numerical approximations to the Hessian.

Dynamics of on-line gradient descent learning for multilayer neural networks

We consider the problem of on-line gradient descent learning for general two-layer neural networks. An analytic solution is presented and used to investigate the role of the learning rate in controlling the evolution and convergence of the learning process.

Measuring performance of virtual learning environment system in higher education

Purpose – The purpose of this paper is to measure the performance of commercial virtual learning environment (VLE) systems, which helps the decision makers to select the appropriate system for their institutions. Design/methodology/approach – This paper develops an integrated multiple criteria decision making approach, which combines the analytic hierarchy process (AHP) and quality function deployment (QFD), to evaluate and select the best system. The evaluating criteria are derived from the requirements of those who use the system. A case study is provided to demonstrate how the integrated approach works. Findings – The major advantage of the integrated approach is that the evaluating criteria are of interest to the stakeholders. This ensures that the selected system will achieve the requirements and satisfy the stakeholders most. Another advantage is that the approach can guarantee the benchmarking to be consistent and reliable. From the case study, it is proved that the performance of a VLE system being used at the university is the best. Therefore, the university should continue to run the system in order to support and facilitate both teaching and learning. Originality/value – It is believed that there is no study that measures the performance of VLE systems, and thus decision makers may have difficulties in system evaluation and selection for their institutions.

Adaptive back-propagation in on-line learning of multilayer networks

An adaptive back-propagation algorithm is studied and compared with gradient descent (standard back-propagation) for on-line learning in two-layer neural networks with an arbitrary number of hidden units. Within a statistical mechanics framework, both numerical studies and a rigorous analysis show that the adaptive back-propagation method results in faster training by breaking the symmetry between hidden units more efficiently and by providing faster convergence to optimal generalization than gradient descent.

Learning with noise and regularizers in multilayer neural networks

We study the effect of two types of noise, data noise and model noise, in an on-line gradient-descent learning scenario for general two-layer student network with an arbitrary number of hidden units. Training examples are randomly drawn input vectors labeled by a two-layer teacher network with an arbitrary number of hidden units. Data is then corrupted by Gaussian noise affecting either the output or the model itself. We examine the effect of both types of noise on the evolution of order parameters and the generalization error in various phases of the learning process.