Exploiting Learning Technologies for World Wide Web Agents

Postprint

Learning Mechanisms for Information Filtering Agents

Postprint

Intelligent Agents = Learning Agents

Postprint

Learning Meta-Descriptions of the FOAF Network

Postprint

Learning from Geometry

Subspaces and manifolds are two powerful models for high dimensional signals. Subspaces model linear correlation and are a good fit to signals generated by physical systems, such as frontal images of human faces and multiple sources impinging at an antenna array. Manifolds model sources that are not linearly correlated, but where signals are determined by a small number of parameters. Examples are images of human faces under different poses or expressions, and handwritten digits with varying styles. However, there will always be some degree of model mismatch between the subspace or manifold model and the true statistics of the source. This dissertation exploits subspace and manifold models as prior information in various signal processing and machine learning tasks.

A near-low-rank Gaussian mixture model measures proximity to a union of linear or affine subspaces. This simple model can effectively capture the signal distribution when each class is near a subspace. This dissertation studies how the pairwise geometry between these subspaces affects classification performance. When model mismatch is vanishingly small, the probability of misclassification is determined by the product of the sines of the principal angles between subspaces. When the model mismatch is more significant, the probability of misclassification is determined by the sum of the squares of the sines of the principal angles. Reliability of classification is derived in terms of the distribution of signal energy across principal vectors. Larger principal angles lead to smaller classification error, motivating a linear transform that optimizes principal angles. This linear transformation, termed TRAIT, also preserves some specific features in each class, being complementary to a recently developed Low Rank Transform (LRT). Moreover, when the model mismatch is more significant, TRAIT shows superior performance compared to LRT.

The manifold model enforces a constraint on the freedom of data variation. Learning features that are robust to data variation is very important, especially when the size of the training set is small. A learning machine with large numbers of parameters, e.g., deep neural network, can well describe a very complicated data distribution. However, it is also more likely to be sensitive to small perturbations of the data, and to suffer from suffer from degraded performance when generalizing to unseen (test) data.

From the perspective of complexity of function classes, such a learning machine has a huge capacity (complexity), which tends to overfit. The manifold model provides us with a way of regularizing the learning machine, so as to reduce the generalization error, therefore mitigate overfiting. Two different overfiting-preventing approaches are proposed, one from the perspective of data variation, the other from capacity/complexity control. In the first approach, the learning machine is encouraged to make decisions that vary smoothly for data points in local neighborhoods on the manifold. In the second approach, a graph adjacency matrix is derived for the manifold, and the learned features are encouraged to be aligned with the principal components of this adjacency matrix. Experimental results on benchmark datasets are demonstrated, showing an obvious advantage of the proposed approaches when the training set is small.

Stochastic optimization makes it possible to track a slowly varying subspace underlying streaming data. By approximating local neighborhoods using affine subspaces, a slowly varying manifold can be efficiently tracked as well, even with corrupted and noisy data. The more the local neighborhoods, the better the approximation, but the higher the computational complexity. A multiscale approximation scheme is proposed, where the local approximating subspaces are organized in a tree structure. Splitting and merging of the tree nodes then allows efficient control of the number of neighbourhoods. Deviation (of each datum) from the learned model is estimated, yielding a series of statistics for anomaly detection. This framework extends the classical {\em changepoint detection} technique, which only works for one dimensional signals. Simulations and experiments highlight the robustness and efficacy of the proposed approach in detecting an abrupt change in an otherwise slowly varying low-dimensional manifold.

Occupant location prediction in smart buildings using association rule mining

Heating, ventilation, air conditioning (HVAC) systems are significant consumers of energy, however building management systems do not typically operate them in accordance with occupant movements. Due to the delayed response of HVAC systems, prediction of occupant locations is necessary to maximize energy efficiency. We present an approach to occupant location prediction based on association rule mining, allowing prediction based on historical occupant locations. Association rule mining is a machine learning technique designed to find any correlations which exist in a given dataset. Occupant location datasets have a number of properties which differentiate them from the market basket datasets that association rule mining was originally designed for. This thesis adapts the approach to suit such datasets, focusing the rule mining process on patterns which are useful for location prediction. This approach, named OccApriori, allows for the prediction of occupants’ next locations as well as their locations further in the future, and can take into account any available data, for example the day of the week, the recent movements of the occupant, and timetable data. By integrating an existing extension of association rule mining into the approach, it is able to make predictions based on general classes of locations as well as specific locations.

El declive de la memoria en "Tu rostro" mañana de Javier Marías: la escritura revivida

Este trabajo tiene como objetivo estudiar los diferentes estados mentales de los personajes de las novelas de Tu rostro mañana, de Javier Marías. Estudiando las reflexiones del narrador sobre J. Deza, Peter Wheeler o Francisco Rico observamos que su decadencia mental se muestra a través de una suerte de ―presciencia‖ o lucidez momentánea que puede servir para mostrar el silencio como única tendencia de todo discurso. Desde el momento en que toda historia de ficción se cimenta sobre un discurso –no importa su cauce de presentación, ni su fuente– este es falsificado por el tiempo, la gente y cualquier otra herramienta que pueda ser utilizada para contar nada. Las conclusiones de este trabajo muestran la quimera que implica tratar de mantener una contención absoluta sobre lo acaecido, pues dicho vacío de narrativas será ocupado por una suplantación que suele ser el reverso más infame de sus actores. Es por ello que el narrador J. Deza sigue conminado a explicar sus historias, incluso allí donde uno diría que ya no puede haber ni palabras suficientes para traducir un hecho en ficción.

Item and task difficulty in a B2 reading examination: perceptions of test-takers and CEFR alignment experts compared with psychometric measurements

The article presents a study of a CEFR B2-level reading subtest that is part of the Slovenian national secondary school leaving examination in English as a foreign language, and compares the test-taker actual performance (objective difficulty) with the test-taker and expert perceptions of item difficulty (subjective difficulty). The study also analyses the test-takers’ comments on item difficulty obtained from a while-reading questionnaire. The results are discussed in the framework of the existing research in the fields of (the assessment of) reading comprehension, and are addressed with regard to their implications for item-writing, FL teaching and curriculum development.

Cyber Enigmas? Passive Detection and Pedagogical Agents: Can Students Spot the fake?

This paper presents a study that was undertaken to examine human interaction with a pedagogical agent and the passive and active detection of such agents within a synchronous, online environment. A pedagogical agent is a software application which can provide a human like interaction using a natural language interface. These may be familiar from the smartphone interfaces such as ‘Siri’ or ‘Cortana’, or the virtual online assistants found on some websites, such as ‘Anna’ on the Ikea website. Pedagogical agents are characters on the computer screen with embodied life-like behaviours such as speech, emotions, locomotion, gestures, and movements of the head, the eye, or other parts of the body. The passive detection test is where participants are not primed to the potential presence of a pedagogical agent within the online environment. The active detection test is where participants are primed to the potential presence of a pedagogical agent. The purpose of the study was to examine how people passively detected pedagogical agents that were presenting themselves as humans in an online environment. In order to locate the pedagogical agent in a realistic higher education online environment, problem-based learning online was used. Problem-based learning online provides a focus for discussions and participation, without creating too much artificiality. The findings indicated that the ways in which students positioned the agent tended to influence the interaction between them. One of the key findings was that since the agent was focussed mainly on the pedagogical task this may have hampered interaction with the students, however some of its non-task dialogue did improve students' perceptions of the autonomous agents’ ability to interact with them. It is suggested that future studies explore the differences between the relationships and interactions of learner and pedagogical agent within authentic situations, in order to understand if students' interactions are different between real and virtual mentors in an online setting.

A review of Parkinson’s disease cardinal and dyskinetic motor symptoms assessment methods using sensor systems

This paper is reviewing objective assessments of Parkinson’s disease(PD) motor symptoms, cardinal, and dyskinesia, using sensor systems. It surveys the manifestation of PD symptoms, sensors that were used for their detection, types of signals (measures) as well as their signal processing (data analysis) methods. A summary of this review’s finding is represented in a table including devices (sensors), measures and methods that were used in each reviewed motor symptom assessment study. In the gathered studies among sensors, accelerometers and touch screen devices are the most widely used to detect PD symptoms and among symptoms, bradykinesia and tremor were found to be mostly evaluated. In general, machine learning methods are potentially promising for this. PD is a complex disease that requires continuous monitoring and multidimensional symptom analysis. Combining existing technologies to develop new sensor platforms may assist in assessing the overall symptom profile more accurately to develop useful tools towards supporting better treatment process.

Distributional effects and individual differences in L2 morphology learning

Second language (L2) learning outcomes may depend on the structure of the input and learners’ cognitive abilities. This study tested whether less predictable input might facilitate learning and generalization of L2 morphology while evaluating contributions of statistical learning ability, nonverbal intelligence, phonological short-term memory, and verbal working memory. Over three sessions, 54 adults were exposed to a Russian case-marking paradigm with a balanced or skewed item distribution in the input. Whereas statistical learning ability and nonverbal intelligence predicted learning of trained items, only nonverbal intelligence also predicted generalization of case-marking inflections to new vocabulary. Neither measure of temporary storage capacity predicted learning. Balanced, less predictable input was associated with higher accuracy in generalization but only in the initial test session. These results suggest that individual differences in pattern extraction play a more sustained role in L2 acquisition than instructional manipulations that vary the predictability of lexical items in the input.

Automated Discovery of Social Networks in Online Learning Communities

As a way to gain greater insights into the operation of online communities, this dissertation applies automated text mining techniques to text-based communication to identify, describe and evaluate underlying social networks among online community members. The main thrust of the study is to automate the discovery of social ties that form between community members, using only the digital footprints left behind in their online forum postings. Currently, one of the most common but time consuming methods for discovering social ties between people is to ask questions about their perceived social ties. However, such a survey is difficult to collect due to the high investment in time associated with data collection and the sensitive nature of the types of questions that may be asked. To overcome these limitations, the dissertation presents a new, content-based method for automated discovery of social networks from threaded discussions, referred to as ‘name network’. As a case study, the proposed automated method is evaluated in the context of online learning communities. The results suggest that the proposed ‘name network’ method for collecting social network data is a viable alternative to costly and time-consuming collection of users’ data using surveys. The study also demonstrates how social networks produced by the ‘name network’ method can be used to study online classes and to look for evidence of collaborative learning in online learning communities. For example, educators can use name networks as a real time diagnostic tool to identify students who might need additional help or students who may provide such help to others. Future research will evaluate the usefulness of the ‘name network’ method in other types of online communities.

Discovery driven analysis on semi-structured text data

Discovery Driven Analysis (DDA) is a common feature of OLAP technology to analyze structured data. In essence, DDA helps analysts to discover anomalous data by highlighting 'unexpected' values in the OLAP cube. By giving indications to the analyst on what dimensions to explore, DDA speeds up the process of discovering anomalies and their causes. However, Discovery Driven Analysis (and OLAP in general) is only applicable on structured data, such as records in databases. We propose a system to extend DDA technology to semi-structured text documents, that is, text documents with a few structured data. Our system pipeline consists of two stages: first, the text part of each document is structured around user specified dimensions, using semi-PLSA algorithm; then, we adapt DDA to these fully structured documents, thus enabling DDA on text documents. We present some applications of this system in OLAP analysis and show how scalability issues are solved. Results show that our system can handle reasonable datasets of documents, in real time, without any need for pre-computation.

SES-RELATED DIFFERENCES IN WORD LEARNING: EFFECTS OF COGNITIVE INHIBITION AND WORD LEARNING

Socioeconomic status (SES) influences language and cognitive development, with discrepancies particularly noticeable in vocabulary development. This study examines how SES-related differences impact the development of syntactic processing, cognitive inhibition, and word learning. 38 4-5-year-olds from higher- and lower-SES backgrounds completed a word-learning task, in which novel words were embedded in active and passive sentences. Critically, unlike the active sentences, all passive sentences required a syntactic revision. Measures of cognitive inhibition were obtained through a modified Stroop task. Results indicate that lower-SES participants had more difficulty using inhibitory functions to resolve conflict compared to their higher-SES counterparts. However, SES did not impact language processing, as the language outcomes were similar across SES background. Additionally, stronger inhibitory processes were related to better language outcomes in the passive sentence condition. These results suggest that cognitive inhibition impact language processing, but this function may vary across children from different SES backgrounds