Speeding up the learning of equivalence classes of Bayesian network structures

R. Daly, Q. Shen and S. Aitken. Speeding up the learning of equivalence classes of Bayesian network structures. Proceedings of the 10th International Conference on Artificial Intelligence and Soft Computing, pages 34-39.

The Advanced Students’ Motivation for Explicit Learning of Grammar

The role of the explicit teaching and learning of grammar in the process of foreign language teaching is a very controversial issue. Language teachers and language teaching methodologists differ in their opinions as to whether grammar should be taught at all and, if so, what is the best way of presenting it. In order to find out students’ opinions on the usefulness of the explicit teaching and learning of grammar a questionnaire was given to fifty-one English majors studying in the Institute of English at Adam Mickiewicz University in Poznań. The results of the questionnaire reveal a very positive attitude on the part of the students towards the explicit learning of grammar. The deductive way of learning seems to be favoured by the majority of the respondents, who also unanimously point to translation as a very effective form of grammar exercise.

Adaptation of Dopamine Neurons' Mismatch Sensitivity Is not Compatible With Reinforcement Learning Theory

Recent electrophysical data inspired the claim that dopaminergic neurons adapt their mismatch sensitivities to reflect variances of expected rewards. This contradicts reward prediction error theory and most basal ganglia models. Application of learning principles points to a testable alternative interpretation-of the same data-that is compatible with existing theory.

Cortical Learning of Recognition Categories: A Resolution of the Exemplar Vs. Prototype Debate

Do humans and animals learn exemplars or prototypes when they categorize objects and events in the world? How are different degrees of abstraction realized through learning by neurons in inferotemporal and prefrontal cortex? How do top-down expectations influence the course of learning? Thirty related human cognitive experiments (the 5-4 category structure) have been used to test competing views in the prototype-exemplar debate. In these experiments, during the test phase, subjects unlearn in a characteristic way items that they had learned to categorize perfectly in the training phase. Many cognitive models do not describe how an individual learns or forgets such categories through time. Adaptive Resonance Theory (ART) neural models provide such a description, and also clarify both psychological and neurobiological data. Matching of bottom-up signals with learned top-down expectations plays a key role in ART model learning. Here, an ART model is used to learn incrementally in response to 5-4 category structure stimuli. Simulation results agree with experimental data, achieving perfect categorization in training and a good match to the pattern of errors exhibited by human subjects in the testing phase. These results show how the model learns both prototypes and certain exemplars in the training phase. ART prototypes are, however, unlike the ones posited in the traditional prototype-exemplar debate. Rather, they are critical patterns of features to which a subject learns to pay attention based on past predictive success and the order in which exemplars are experienced. Perturbations of old memories by newly arriving test items generate a performance curve that closely matches the performance pattern of human subjects. The model also clarifies exemplar-based accounts of data concerning amnesia.

Task-Irrelevant Perceptual Learning Specific to the Contrast Polarity of Motion Stimuli

Studies of perceptual learning have focused on aspects of learning that are related to early stages of sensory processing. However, conclusions that perceptual learning results in low-level sensory plasticity are of great controversy, largely because such learning can often be attributed to plasticity in later stages of sensory processing or in the decision processes. To address this controversy, we developed a novel random dot motion (RDM) stimulus to target motion cells selective to contrast polarity, by ensuring the motion direction information arises only from signal dot onsets and not their offsets, and used these stimuli in conjunction with the paradigm of task-irrelevant perceptual learning (TIPL). In TIPL, learning is achieved in response to a stimulus by subliminally pairing that stimulus with the targets of an unrelated training task. In this manner, we are able to probe learning for an aspect of motion processing thought to be a function of directional V1 simple cells with a learning procedure that dissociates the learned stimulus from the decision processes relevant to the training task. Our results show learning for the exposed contrast polarity and that this learning does not transfer to the unexposed contrast polarity. These results suggest that TIPL for motion stimuli may occur at the stage of directional V1 simple cells.

Brain Learning and Recognition: The Large and the Small of It in Inferotemporal Cortex

Anterior inferotemporal cortex (ITa) plays a key role in visual object recognition. Recognition is tolerant to object position, size, and view changes, yet recent neurophysiological data show ITa cells with high object selectivity often have low position tolerance, and vice versa. A neural model learns to simulate both this tradeoff and ITa responses to image morphs using large-scale and small-scale IT cells whose population properties may support invariant recognition.

Cortical Dynamics of Contextually-Cued Attentive Visual Learning and Search: Spatial and Object Evidence Accumulation

How do humans use predictive contextual information to facilitate visual search? How are consistently paired scenic objects and positions learned and used to more efficiently guide search in familiar scenes? For example, a certain combination of objects can define a context for a kitchen and trigger a more efficient search for a typical object, such as a sink, in that context. A neural model, ARTSCENE Search, is developed to illustrate the neural mechanisms of such memory-based contextual learning and guidance, and to explain challenging behavioral data on positive/negative, spatial/object, and local/distant global cueing effects during visual search. The model proposes how global scene layout at a first glance rapidly forms a hypothesis about the target location. This hypothesis is then incrementally refined by enhancing target-like objects in space as a scene is scanned with saccadic eye movements. The model clarifies the functional roles of neuroanatomical, neurophysiological, and neuroimaging data in visual search for a desired goal object. In particular, the model simulates the interactive dynamics of spatial and object contextual cueing in the cortical What and Where streams starting from early visual areas through medial temporal lobe to prefrontal cortex. After learning, model dorsolateral prefrontal cortical cells (area 46) prime possible target locations in posterior parietal cortex based on goalmodulated percepts of spatial scene gist represented in parahippocampal cortex, whereas model ventral prefrontal cortical cells (area 47/12) prime possible target object representations in inferior temporal cortex based on the history of viewed objects represented in perirhinal cortex. The model hereby predicts how the cortical What and Where streams cooperate during scene perception, learning, and memory to accumulate evidence over time to drive efficient visual search of familiar scenes.

ARTMAP: Supervised Real-Time Learning and Classification of Nonstationary Data by a Self-Organizing Neural Network

This article introduces a new neural network architecture, called ARTMAP, that autonomously learns to classify arbitrarily many, arbitrarily ordered vectors into recognition categories based on predictive success. This supervised learning system is built up from a pair of Adaptive Resonance Theory modules (ARTa and ARTb) that are capable of self-organizing stable recognition categories in response to arbitrary sequences of input patterns. During training trials, the ARTa module receives a stream {a^(p)} of input patterns, and ARTb receives a stream {b^(p)} of input patterns, where b^(p) is the correct prediction given a^(p). These ART modules are linked by an associative learning network and an internal controller that ensures autonomous system operation in real time. During test trials, the remaining patterns a^(p) are presented without b^(p), and their predictions at ARTb are compared with b^(p). Tested on a benchmark machine learning database in both on-line and off-line simulations, the ARTMAP system learns orders of magnitude more quickly, efficiently, and accurately than alternative algorithms, and achieves 100% accuracy after training on less than half the input patterns in the database. It achieves these properties by using an internal controller that conjointly maximizes predictive generalization and minimizes predictive error by linking predictive success to category size on a trial-by-trial basis, using only local operations. This computation increases the vigilance parameter ρa of ARTa by the minimal amount needed to correct a predictive error at ARTb· Parameter ρa calibrates the minimum confidence that ARTa must have in a category, or hypothesis, activated by an input a^(p) in order for ARTa to accept that category, rather than search for a better one through an automatically controlled process of hypothesis testing. Parameter ρa is compared with the degree of match between a^(p) and the top-down learned expectation, or prototype, that is read-out subsequent to activation of an ARTa category. Search occurs if the degree of match is less than ρa. ARTMAP is hereby a type of self-organizing expert system that calibrates the selectivity of its hypotheses based upon predictive success. As a result, rare but important events can be quickly and sharply distinguished even if they are similar to frequent events with different consequences. Between input trials ρa relaxes to a baseline vigilance pa When ρa is large, the system runs in a conservative mode, wherein predictions are made only if the system is confident of the outcome. Very few false-alarm errors then occur at any stage of learning, yet the system reaches asymptote with no loss of speed. Because ARTMAP learning is self stabilizing, it can continue learning one or more databases, without degrading its corpus of memories, until its full memory capacity is utilized.

Assessing segmentation processes by click detection: online measure of statistical learning, or simple interference?

Statistical learning can be used to extract the words from continuous speech. Gómez, Bion, and Mehler (Language and Cognitive Processes, 26, 212–223, 2011) proposed an online measure of statistical learning: They superimposed auditory clicks on a continuous artificial speech stream made up of a random succession of trisyllabic nonwords. Participants were instructed to detect these clicks, which could be located either within or between words. The results showed that, over the length of exposure, reaction times (RTs) increased more for within-word than for between-word clicks. This result has been accounted for by means of statistical learning of the between-word boundaries. However, even though statistical learning occurs without an intention to learn, it nevertheless requires attentional resources. Therefore, this process could be affected by a concurrent task such as click detection. In the present study, we evaluated the extent to which the click detection task indeed reflects successful statistical learning. Our results suggest that the emergence of RT differences between within- and between-word click detection is neither systematic nor related to the successful segmentation of the artificial language. Therefore, instead of being an online measure of learning, the click detection task seems to interfere with the extraction of statistical regularities.

Use of Web Logs (Blogs) in Learning Environments: Blogs for Student Support

Innovation in technology and communications and particularly the advent of the Web is changing the structure of teaching and learning today. While there is much debate about the use of technology in learning and how e-learning is creating new approaches to delivery of learning there is been very little if any work on the use of of the emerging technologies in providing student support through their learning process. This paper reports on research and development undertaken by the eCentre based at the University of Greenwich School Of Computing in designing and developing a "Project Blog System" in order to address some long standing issues related to supervision of final year degree student projects. The paper will report on the methodology used to design the system and will discuss some of the results from students and staff evaluation of the system developed.

Staff training in the mental health needs of people with learning disabilities in the UK

This paper gives a general overview of some of the factors involved in the training and knowledge of learning disabilities staff relating to mental health. Early indications from research have shown that training may be effective as a way of addressing these problems, but further research and clear guidance on best practice in implementing staff training are needed in this important area.

Reflective practice: the enduring influence of Kolb’s Experiential Learning Theory

Since 1984 David Kolb’s Experiential Learning Theory (ELT) has been a leading influence in the development of learner-centred pedagogy in management and business. It forms the basis of Kolb’s own Learning Styles’ Inventory and those of other authors including Honey and Mumford (2000). It also provides powerful underpinning for the emphasis, nay insistence, on reflection as a way of learning and the use of reflective practice in the preparation of students for business and management and other professions. In this paper, we confirm that Kolb’s ELT is still the most commonly cited source used in relation to reflective practice. Kolb himself continues to propound its relevance to teaching and learning in general. However, we also review some of the criticisms that ELT has attracted over the years and advance new criticisms that challenge its relevance to higher education and its validity as a model for formal, intentional learning.

Reaching across organisational, sectoral and geographical boundaries: exploring the learning potential of an EU cross-border project

Research This paper outlines some of the key findings from an evaluation of the project and demonstrates that EC funded projects such as this, which seek to promote cross border collaboration and understanding (i.e. across organisational, sectoral and geographical boundaries) offer considerable learning potential – not least about variances in health politics across different communities. However, for this learning to be realised a comprehensive system of knowledge management needs to be an integral part of project planning alongside a system for sustaining embryonic professional networks. The concept of managing relationships was also a key part of the projects success. Executing a project funded by the EU demands the development of complex organisational skills to negotiate all the administrative challenges en route to successful completion and this project in particular relied for its success on the development of social relationships of trust and mutual respect across national, professional and social boundaries. Context A three–year European Commission funded project designed to exchange a wide range of staff (professional semiprofessional and voluntary staff in health and social care) project led by the University of Greenwich (UK) and the Université Catholique de Lille, France was completed this year (February 2008). The project was complex because it involved working in different national contexts, was multi-disciplinary, and demanded the negotiation of multiple boundaries. Theories A mixed method evaluation including written reports gathered immediately after each exchange visit and a post hoc series of individual interviews and focus groups was conducted in order to gain qualitative information (from the participants perspective) on their experiences and to identify any learning gained. Results Analysis of the data provided evidence of learning on a number of levels; personally, inter and intra professionally and organisationally as well as across sectors and also from a project management perspective. The learning crystallised around the extent of the differences noted by the participants between the UK and the French health and social care systems despite geographical proximity, common membership of the EU and many shared challenges in health and social care. The extent of these differences, noted at every level from policy to practice proved a rich source for reflection on organisational philosophies, ways of working, distribution of resources, professional roles and autonomy and professional registration and mobility - in short on health politics at ‘macro’ and ‘micro’ levels.

The eLIDA CAMEL nomadic model of collaborative partnership for a community of practice in design for learning

A nomadic collaborative partnership model for a community of practice (CoP) in Design for Learning (D4L) can facilitate successful innovation and continuing appraisals of effective professional practice, stimulated by a 'critical friend' assigned to the project. This paper reports on e-learning case studies collected by the JISC-funded UK eLIDA CAMEL Design for Learning Project. The project implemented and evaluated learning design (LD) tools in higher and further education within the JISC Design for Learning pedagogic programme (2006-07). Project partners trialled professional user evaluations of innovative e-learning tools with learning design function, collecting D4L case studies and LD sequences in post-16/HE contexts using LAMS and Moodle. The project brought together learning activity sequences within a collaborative e-learning community of practice based on the CAMEL (Collaborative Approaches to the Management of e-Learning) model, contributing to international D4L developments. This paper provides an overview of project outputs in e-learning innovations, including evaluations from teachers and students. The paper explores intentionality in the development of a CoP in design for learning, reporting on trials of LD and social software that bridged tensions between formalised intra-institutional e-learning relationships and inter-institutional professional project team dynamic D4L practitioner interactions. Following a brief report of D4L case studies and feedback, the catalytic role of the 'critical friend' is highlighted and recommended as a key ingredient in the successful development of a nomadic model of communities of practice for managing professional e-learning projects. eLIDA CAMEL Partners included the Association of Learning Technology (ALT), JISC infoNet, three universities and five FE/Sixth Form Colleges. Results reported to JISC demonstrated D4L e-learning innovations by practitioners, illuminated by the role of the 'critical friend'. The project also benefited from formal case study evaluations and the leading work of ALT and JISC infoNet in the development of the CAMEL model.

Student Experience of E-Learning (SEEL)

The Student Experience of E-Learning project (SEEL) was an institutional response to the university’s HEA/JISC Benchmarking exercise (Ryan and Kandler, 2007). The study had a social constructivist approach which recognised the importance of listening to the student voice (JISC 2007) within the University of Greenwich context, to interpret the student experience of e-learning. Nearly 1000 students responded to an online survey on their approaches to, and their use of, learning technology. The quantitative and qualitative questions used included identifying study patterns, using specific online tools, within the context of learning and beyond, and student’s attitudes towards using e-learning in their studies. Initially, individual responses to questions were analysed in depth, giving a general indication of the student experience. Further depth was applied through a filtering mechanism, beginning with a cross-slicing of individual student responses to produce cameos. Audio logs and individual interviews were drawn from these cameos. Analysis of the cameos is in progress but has already revealed some unexpected results. There was a mismatch between students’ expectations of the university’s use of technology and their experiences and awareness of its possible use in other contexts. Students recognised the importance of social interaction as a vehicle for learning (Vygotsky 1978, Bruner 2006) but expressed polarised views on the use of social networking sites such as Facebook for e-learning. Their experiences in commercial contexts led them to see the university VLE as unimaginative and the tutors’ use of it as lacking in vision. Whereas analysis of the individual questions provided a limited picture, the cameos gave a truer reflection of the students lived experiences and identified a gulf between the university’s provision and the students’ expectation of e-learning and their customary use of technology. However it is recognised that the very nature of an online survey necessarily excludes students who chose not to engage, either through lack of skills or through disillusionment and this would constitute a separate area for study.