Neural network learning:theoretical foundations

This important work describes recent theoretical advances in the study of artificial neural networks. It explores probabilistic models of supervised learning problems, and addresses the key statistical and computational questions. Chapters survey research on pattern classification with binary-output networks, including a discussion of the relevance of the Vapnik Chervonenkis dimension, and of estimates of the dimension for several neural network models. In addition, Anthony and Bartlett develop a model of classification by real-output networks, and demonstrate the usefulness of classification with a "large margin." The authors explain the role of scale-sensitive versions of the Vapnik Chervonenkis dimension in large margin classification, and in real prediction. Key chapters also discuss the computational complexity of neural network learning, describing a variety of hardness results, and outlining two efficient, constructive learning algorithms. The book is self-contained and accessible to researchers and graduate students in computer science, engineering, and mathematics

Increasing learners’ satisfaction/intention to adopt more e-learning

Purpose: E-learning is an organisationally risky investment given the cost and poor levels of adoption by users. In order to gain a better understanding of this problem, a study was conducted into the use of e-learning in a rail organisation. Design/methodology/approach: Using an online survey, employees of a rail-sector organisation were questioned about their use and likelihood of adoption of e-learning. This study explores the factors that affect the way in which learners experience and perceive such systems. Using statistical analysis, twelve hypotheses are tested and explored. Relationships between learning satisfaction, intention to adopt and the characteristics of e-learning systems were established. Findings: The study found that e-learning characteristics can buffer the relationship between learner characteristics and intention to adopt further e-learning in the future. Further, we found that high levels of support can compensate individuals who are low in technological efficacy to adopt e-learning. Research limitations/implications: The cross-sectional design of the study and its focus on measuring intention to adopt as opposed to actual adoption are both limitations. Future research using longitudinal design and research employing a time lag design measuring actual adoption as well as intention are recommended. Practical implications: From a practical perspective, organizations can focus on the actual content and authenticity of the learning experience delivered by the e-learning system to significantly impact how employees will perceive and use e-learning in the future. Low technological efficacy individuals tend not to adopt new technology. Instead of changing individuals’ personalities, organizations can implement supportive policies and practices which would lead to higher e-learning adoption rate among low efficacy individuals. Originality/value: The study integrates technology adoption and learning literatures in developing enablers for e-learning in organizations. Further, this study collects data from rail employees, and therefore the findings are practical to an industry.

Exploring the conditions to support assessment for more equitable learning outcomes

NAPLAN RESULTS HAVE gained socio-political prominence and have been used as indicators of educational outcomes for all students, including Indigenous students. Despite the promise of open and in-depth access to NAPLAN data as a vehicle for intervention, we argue that the use of NAPLAN data as a basis for teachers and schools to reduce variance in learning outcomes is insufficient. NAPLAN tests are designed to show statistical variance at the level of the school and the individual, yet do not factor in the sociocultural and cognitive conditions Indigenous students’ experience when taking the tests. We contend that further understanding of these influences may help teachers understand how to develop their classroom practices to secure better numeracy and literacy outcomes for all students. Empirical research findings demonstrate how teachers can develop their classroom practices from an understanding of the extraneous cognitive load imposed by test taking. We have analysed Indigenous students’ experience of solving mathematical test problems to discover evidence of extraneous cognitive load. We have also explored conditions that are more supportive of learning derived from a classroom intervention which provides an alternative way to both assess and build learning for Indigenous students. We conclude that conditions to support assessment for more equitable learning outcomes require a reduction in cognitive load for Indigenous students while maintaining a high level of expectation and participation in problem solving.

University students’ perspective on blended learning

This research project aimed to explore students’ perspective on an appropriate mix of online and-face-to-face activities in a master’s programme in library and information science at an Australian university. Identifying aspects that students evaluate as supportive, challenging and efficient in their learning is important for the design of an appropriate mix in blended learning courses. Twenty-three master’s students responded to a questionnaire containing 40 open-ended and closed questions. Applying both statistical and content analysis provides a deeper understanding of students’ responses. Students like the flexibility and the convenience of online learning, but also the possibilities of face-to-face interaction with teachers and peers for building personal learning networks. Students expect an equal quality of learning delivery and criticised the quality of online participation and lecture recordings. Blended learning is an approach that supports a range of learning styles and life styles.

Characterising an ECG signal using statistical modelling : a feasibility study

For clinical use, in electrocardiogram (ECG) signal analysis it is important to detect not only the centre of the P wave, the QRS complex and the T wave, but also the time intervals, such as the ST segment. Much research focused entirely on qrs complex detection, via methods such as wavelet transforms, spline fitting and neural networks. However, drawbacks include the false classification of a severe noise spike as a QRS complex, possibly requiring manual editing, or the omission of information contained in other regions of the ECG signal. While some attempts were made to develop algorithms to detect additional signal characteristics, such as P and T waves, the reported success rates are subject to change from person-to-person and beat-to-beat. To address this variability we propose the use of Markov-chain Monte Carlo statistical modelling to extract the key features of an ECG signal and we report on a feasibility study to investigate the utility of the approach. The modelling approach is examined with reference to a realistic computer generated ECG signal, where details such as wave morphology and noise levels are variable.

From policy borrowing to implementation : an illuminative evaluation of learning and teaching in higher education in Australia (2002 to 2008)

This study documents and theorises the consequences of the 2003 Australian Government Reform Package focussed on learning and teaching in Higher Education during the period 2002 to 2008. This is achieved through the perspective of program evaluation and the methodology of illuminative evaluation. The findings suggest that the three national initiatives of that time, Learning and Teaching Performance Fund (LTPF), Australian Learning and Teaching Council (ALTC), and Australian Universities Quality Agency (AUQA), were successful in repositioning learning and teaching as a core activity in universities. However, there were unintended consequences brought about by international policy borrowing, when the short-lived nature of LTPF suggests a legacy of quality compliance rather than one of quality enrichment.

Learning through modelling in the primary years

Many nations are highlighting the need for a renaissance in the mathematical sciences as essential to the well-being of all citizens (e.g., Australian Academy of Science, 2006; 2010; The National Academies, 2009). Indeed, the first recommendation of The National Academies’ Rising Above the Storm (2007) was to vastly improve K–12 science and mathematics education. The subsequent report, Rising Above the Gathering Storm Two Years Later (2009), highlighted again the need to target mathematics and science from the earliest years of schooling: “It takes years or decades to build the capability to have a society that depends on science and technology . . . You need to generate the scientists and engineers, starting in elementary and middle school” (p. 9). Such pleas reflect the rapidly changing nature of problem solving and reasoning needed in today’s world, beyond the classroom. As The National Academies (2009) reported, “Today the problems are more complex than they were in the 1950s, and more global. They’ll require a new educated workforce, one that is more open, collaborative, and cross-disciplinary” (p. 19). The implications for the problem solving experiences we implement in schools are far-reaching. In this chapter, I consider problem solving and modelling in the primary school, beginning with the need to rethink the experiences we provide in the early years. I argue for a greater awareness of the learning potential of young children and the need to provide stimulating learning environments. I then focus on data modelling as a powerful means of advancing children’s statistical reasoning abilities, which they increasingly need as they navigate their data-drenched world.

Machine learning approaches to analysing textual injury surveillance data: A systematic review

Objective To synthesise recent research on the use of machine learning approaches to mining textual injury surveillance data. Design Systematic review. Data sources The electronic databases which were searched included PubMed, Cinahl, Medline, Google Scholar, and Proquest. The bibliography of all relevant articles was examined and associated articles were identified using a snowballing technique. Selection criteria For inclusion, articles were required to meet the following criteria: (a) used a health-related database, (b) focused on injury-related cases, AND used machine learning approaches to analyse textual data. Methods The papers identified through the search were screened resulting in 16 papers selected for review. Articles were reviewed to describe the databases and methodology used, the strength and limitations of different techniques, and quality assurance approaches used. Due to heterogeneity between studies meta-analysis was not performed. Results Occupational injuries were the focus of half of the machine learning studies and the most common methods described were Bayesian probability or Bayesian network based methods to either predict injury categories or extract common injury scenarios. Models were evaluated through either comparison with gold standard data or content expert evaluation or statistical measures of quality. Machine learning was found to provide high precision and accuracy when predicting a small number of categories, was valuable for visualisation of injury patterns and prediction of future outcomes. However, difficulties related to generalizability, source data quality, complexity of models and integration of content and technical knowledge were discussed. Conclusions The use of narrative text for injury surveillance has grown in popularity, complexity and quality over recent years. With advances in data mining techniques, increased capacity for analysis of large databases, and involvement of computer scientists in the injury prevention field, along with more comprehensive use and description of quality assurance methods in text mining approaches, it is likely that we will see a continued growth and advancement in knowledge of text mining in the injury field.

The paradox of creative uncertainty in learning and teaching

In an ever-changing and globalised world there is a need for higher education to adapt and evolve its models of learning and teaching. The old industrial model has lost traction, and new patterns of creative engagement are required. These new models potentially increase relevancy and better equip students for the future. Although creativity is recognised as an attribute that can contribute much to the development of these pedagogies, and creativity is valued by universities as a graduate capability, some educators understandably struggle to translate this vision into practice. This paper reports on selected survey findings from a mixed methods research project which aimed to shed light on how creativity can be designed for in higher education learning and teaching settings. A social constructivist epistemology underpinned the research and data was gathered using survey and case study methods. Descriptive statistical methods and informed grounded theory were employed for the analysis reported here. The findings confirm that creativity is valued for its contribution to the development of students’ academic work, employment opportunities and life in general; however, tensions arise between individual educator’s creative pedagogical goals and the provision of institutional support for implementation of those objectives. Designing for creativity becomes, paradoxically, a matter of navigating and limiting complexity and uncertainty, while simultaneously designing for those same states or qualities.

Learning with symmetric label noise: The importance of being unhinged

Convex potential minimisation is the de facto approach to binary classification. However, Long and Servedio [2008] proved that under symmetric label noise (SLN), minimisation of any convex potential over a linear function class can result in classification performance equivalent to random guessing. This ostensibly shows that convex losses are not SLN-robust. In this paper, we propose a convex, classification-calibrated loss and prove that it is SLN-robust. The loss avoids the Long and Servedio [2008] result by virtue of being negatively unbounded. The loss is a modification of the hinge loss, where one does not clamp at zero; hence, we call it the unhinged loss. We show that the optimal unhinged solution is equivalent to that of a strongly regularised SVM, and is the limiting solution for any convex potential; this implies that strong l2 regularisation makes most standard learners SLN-robust. Experiments confirm the unhinged loss’ SLN-robustness.