Active learning of model evidence using Bayesian quadrature

Numerical integration is a key component of many problems in scientific computing, statistical modelling, and machine learning. Bayesian Quadrature is a modelbased method for numerical integration which, relative to standard Monte Carlo methods, offers increased sample efficiency and a more robust estimate of the uncertainty in the estimated integral. We propose a novel Bayesian Quadrature approach for numerical integration when the integrand is non-negative, such as the case of computing the marginal likelihood, predictive distribution, or normalising constant of a probabilistic model. Our approach approximately marginalises the quadrature model's hyperparameters in closed form, and introduces an active learning scheme to optimally select function evaluations, as opposed to using Monte Carlo samples. We demonstrate our method on both a number of synthetic benchmarks and a real scientific problem from astronomy.

Generalizing on Multiple Grounds: Performance Learning in Model-Based Technology

This thesis explores ways to augment a model-based diagnostic program with a learning component, so that it speeds up as it solves problems. Several learning components are proposed, each exploiting a different kind of similarity between diagnostic examples. Through analysis and experiments, we explore the effect each learning component has on the performance of a model-based diagnostic program. We also analyze more abstractly the performance effects of Explanation-Based Generalization, a technology that is used in several of the proposed learning components.

From Aspiration to Action: A Learning Intentions Model to Promote Critical Engagement with Science in the Print-Based Media

Science programmes which prepare students to read critically and respond thoughtfully to science-based reports in the media could play an important role in promoting informed participation in the public debate about issues relating to science, technology and society. Evidence based guidance about the practice and pattern of use of science-based media in the classroom is limited. This study sought to identify learning intentions that teachers believe ought to underpin the development of programmes of study designed to achieve this end-result. Teachers views of knowledge, skills and attitudes required to engage critically with science-based news served as a basis for this study. Teachers developed a pedagogical model by selecting appropriate statements of learning intentions, grouping these into coherent and manageable themes and coding them according to perceived level of difficulty. The model is largely compatible with current curricular provision in the UK, highlights opportunities for interdisciplinary collaboration and illustrates the developmental nature of the topic.

Telephone survey evaluation of the educational impact of a distance learning course

The educational impact of a distance learning (DL) course entitled ''Health Screening for Health Promotion, was investigated using a telephone questionnaire survey. An introduction to the DL course was distributed to all community pharmacists in England (16,400); the main body of the course, on which pharmacists were examined, was distributed free of charge to all pharmacists who requested it (1,485). Pharmacists participating in the survey (868) were organized by random selection into groups and stratified according to age, sex and postcode. A matched control group was randomly drawn from those pharmacists who had not participated in the course. The DL course improved pharmacists' knowledge about health screening/health promotion issues (e.g., mean score of 66 percent achieved by a group who had completed the course; 51 percent achieved by the control group; P<0.001). Factors influencing score achieved included sex and year of registration. Males performed better than females (P<0.008) while performance decreased with number of years on the register (P<0.001).

Machine learning Vasicek model calibration with Gaussian processes

In this article, we calibrate the Vasicek interest rate model under the risk neutral measure by learning the model parameters using Gaussian processes for machine learning regression. The calibration is done by maximizing the likelihood of zero coupon bond log prices, using mean and covariance functions computed analytically, as well as likelihood derivatives with respect to the parameters. The maximization method used is the conjugate gradients. The only prices needed for calibration are zero coupon bond prices and the parameters are directly obtained in the arbitrage free risk neutral measure.

An Ontario-Developed Online Special Education Teacher Course Model for China

This study investigated the effectiveness of an Ontario-developed online Special Education teacher training course as a model for in-service teacher professional development in China. The study employed a mixed method approach encompassing both a quantitative survey and a qualitative research component to gather perceptions of Chinese and Canadian teachers, educational administrators, and teacher-educators who have intensive experience with online education, Special Education, and teacher preparation programs both in China and Canada. The study revealed insufficient understanding of Special Education among the general Chinese population, underdevelopment of Special Education teacher preparation in China, and potential benefits of using a Canadian online teacher training course as a model for Special Education in China. Based on the literature review and the results of this study, it is concluded that online Canadian Special Education teacher in-service courses can set an example for Chinese Special Education teacher training. A caveat is that such courses would require localized modifications, support of educational authorities, and pilot testing.

Neurofuzzy mixture of experts network parallel learning and model construction algorithms

A connection between a fuzzy neural network model with the mixture of experts network (MEN) modelling approach is established. Based on this linkage, two new neuro-fuzzy MEN construction algorithms are proposed to overcome the curse of dimensionality that is inherent in the majority of associative memory networks and/or other rule based systems. The first construction algorithm employs a function selection manager module in an MEN system. The second construction algorithm is based on a new parallel learning algorithm in which each model rule is trained independently, for which the parameter convergence property of the new learning method is established. As with the first approach, an expert selection criterion is utilised in this algorithm. These two construction methods are equivalent in their effectiveness in overcoming the curse of dimensionality by reducing the dimensionality of the regression vector, but the latter has the additional computational advantage of parallel processing. The proposed algorithms are analysed for effectiveness followed by numerical examples to illustrate their efficacy for some difficult data based modelling problems.

Pupils' Interaction with the Exhibits According to the Learning Behaviour Model

Science centres are one of the best opportunities for informal study of natural science. There are many advantages to learn in the science centres compared with the traditional methods: it is possible to motivate and supply visitors with the social experience, to improve people’s understandings and attitudes, thereby bringing on and attaching wider interest towards natural science. In the science centres, pupils show interest, enthusiasm, motivation, self-confidence, sensitiveness and also they are more open and eager to learn. Traditional school-classes however mostly do not favour these capabilities. This research presents the qualitative study in the science centre. Data was gathered from observations and interviews at Science North science centre in Canada. Pupils’ learning behaviours were studied at different exhibits in the science centre. Learning behaviours are classified as follows: labels reading, experimenting with the exhibits, observing others or exhibit, using guide, repeating the activity, positive emotional response, acknowledged relevance, seeking and sharing information. In this research, it became clear that in general pupils do not read labels; in most cases pupils do not use the guides help; pupils prefer exhibits that enable high level of interactivity; pupils display more learning behaviours at exhibits that enable a high level of interactivity.

Improving web learning through model optimization using bootstrap for a tour-guide robot

We perform a review of Web Mining techniques and we describe a Bootstrap Statistics methodology applied to pattern model classifier optimization and verification for Supervised Learning for Tour-Guide Robot knowledge repository management. It is virtually impossible to test thoroughly Web Page Classifiers and many other Internet Applications with pure empirical data, due to the need for human intervention to generate training sets and test sets. We propose using the computer-based Bootstrap paradigm to design a test environment where they are checked with better reliability.

Personal knowledge development in online learning:a model for measuring externalisation, combination and internalisation

This paper presents a model for measuring personal knowledge development in online learning environments. It is based on Nonaka‘s SECI model of organisational knowledge creation. It is argued that Socialisation is not a relevant mode in the context of online learning and was therefore not covered in the measurement instrument. Therefore, the remaining three of SECI‘s knowledge conversion modes, namely Externalisation, Combination, and Internalisation were used and a measurement instrument was created which also examines the interrelationships between the three modes. Data was collected using an online survey, in which online learners report on their experiences of personal knowledge development in online learning environments. In other words, the instrument measures the magnitude of online learners‘ Externalisation and combination activities as well as their level of internalisation, which is the outcome of their personal knowledge development in online learning.

Evolution, recurrency and kernels in learning to model inflation

This paper provides the most fully comprehensive evidence to date on whether or not monetary aggregates are valuable for forecasting US inflation in the early to mid 2000s. We explore a wide range of different definitions of money, including different methods of aggregation and different collections of included monetary assets. We use non-linear, artificial intelligence techniques, namely, recurrent neural networks, evolution strategies and kernel methods in our forecasting experiment. In the experiment, these three methodologies compete to find the best fitting US inflation forecasting models and are then compared to forecasts from a naive random walk model. The best models were non-linear autoregressive models based on kernel methods. Our findings do not provide much support for the usefulness of monetary aggregates in forecasting inflation. There is evidence in the literature that evolutionary methods can be used to evolve kernels hence our future work should combine the evolutionary and kernel methods to get the benefits of both.