Auditory middle latency response and phonological awareness in students with learning disabilities

Introduction Behavioral tests of auditory processing have been applied in schools and highlight the association between phonological awareness abilities and auditory processing, confirming that low performance on phonological awareness tests may be due to low performance on auditory processing tests. Objective To characterize the auditory middle latency response and the phonological awareness tests and to investigate correlations between responses in a group of children with learning disorders. Methods The study included 25 students with learning disabilities. Phonological awareness and auditory middle latency response were tested with electrodes placed on the left and right hemispheres. The correlation between the measurements was performed using the Spearman rank correlation coefficient. Results There is some correlation between the tests, especially between the Pa component and syllabic awareness, where moderate negative correlation is observed. Conclusion In this study, when phonological awareness subtests were performed, specifically phonemic awareness, the students showed a low score for the age group, although for the objective examination, prolonged Pa latency in the contralateral via was observed. Negative weak to moderate correlation for Pa wave latency was observed, as was positive weak correlation for Na-Pa amplitude.

Semi-supervised learning guided by the modularity measure in complex networks

Semi-supervised learning techniques have gained increasing attention in the machine learning community, as a result of two main factors: (1) the available data is exponentially increasing; (2) the task of data labeling is cumbersome and expensive, involving human experts in the process. In this paper, we propose a network-based semi-supervised learning method inspired by the modularity greedy algorithm, which was originally applied for unsupervised learning. Changes have been made in the process of modularity maximization in a way to adapt the model to propagate labels throughout the network. Furthermore, a network reduction technique is introduced, as well as an extensive analysis of its impact on the network. Computer simulations are performed for artificial and real-world databases, providing a numerical quantitative basis for the performance of the proposed method.

Using Machine Learning Classifiers to Assist Healthcare-Related Decisions: Classification of Electronic Patient Records

Surveillance Levels (SLs) are categories for medical patients (used in Brazil) that represent different types of medical recommendations. SLs are defined according to risk factors and the medical and developmental history of patients. Each SL is associated with specific educational and clinical measures. The objective of the present paper was to verify computer-aided, automatic assignment of SLs. The present paper proposes a computer-aided approach for automatic recommendation of SLs. The approach is based on the classification of information from patient electronic records. For this purpose, a software architecture composed of three layers was developed. The architecture is formed by a classification layer that includes a linguistic module and machine learning classification modules. The classification layer allows for the use of different classification methods, including the use of preprocessed, normalized language data drawn from the linguistic module. We report the verification and validation of the software architecture in a Brazilian pediatric healthcare institution. The results indicate that selection of attributes can have a great effect on the performance of the system. Nonetheless, our automatic recommendation of surveillance level can still benefit from improvements in processing procedures when the linguistic module is applied prior to classification. Results from our efforts can be applied to different types of medical systems. The results of systems supported by the framework presented in this paper may be used by healthcare and governmental institutions to improve healthcare services in terms of establishing preventive measures and alerting authorities about the possibility of an epidemic.

Combining meta-learning and search techniques to select parameters for support vector machines

Support Vector Machines (SVMs) have achieved very good performance on different learning problems. However, the success of SVMs depends on the adequate choice of the values of a number of parameters (e.g., the kernel and regularization parameters). In the current work, we propose the combination of meta-learning and search algorithms to deal with the problem of SVM parameter selection. In this combination, given a new problem to be solved, meta-learning is employed to recommend SVM parameter values based on parameter configurations that have been successfully adopted in previous similar problems. The parameter values returned by meta-learning are then used as initial search points by a search technique, which will further explore the parameter space. In this proposal, we envisioned that the initial solutions provided by meta-learning are located in good regions of the search space (i.e. they are closer to optimum solutions). Hence, the search algorithm would need to evaluate a lower number of candidate solutions when looking for an adequate solution. In this work, we investigate the combination of meta-learning with two search algorithms: Particle Swarm Optimization and Tabu Search. The implemented hybrid algorithms were used to select the values of two SVM parameters in the regression domain. These combinations were compared with the use of the search algorithms without meta-learning. The experimental results on a set of 40 regression problems showed that, on average, the proposed hybrid methods obtained lower error rates when compared to their components applied in isolation.

Stochastic competitive learning in complex networks

Competitive learning is an important machine learning approach which is widely employed in artificial neural networks. In this paper, we present a rigorous definition of a new type of competitive learning scheme realized on large-scale networks. The model consists of several particles walking within the network and competing with each other to occupy as many nodes as possible, while attempting to reject intruder particles. The particle's walking rule is composed of a stochastic combination of random and preferential movements. The model has been applied to solve community detection and data clustering problems. Computer simulations reveal that the proposed technique presents high precision of community and cluster detections, as well as low computational complexity. Moreover, we have developed an efficient method for estimating the most likely number of clusters by using an evaluator index that monitors the information generated by the competition process itself. We hope this paper will provide an alternative way to the study of competitive learning.

Non-Dominated Sorting Genetic Algorithm Based on Reinforcement Learning to Optimization of Broad-Band Reflector Antennas Satellite

This paper aims to provide an improved NSGA-II (Non-Dominated Sorting Genetic Algorithm-version II) which incorporates a parameter-free self-tuning approach by reinforcement learning technique, called Non-Dominated Sorting Genetic Algorithm Based on Reinforcement Learning (NSGA-RL). The proposed method is particularly compared with the classical NSGA-II when applied to a satellite coverage problem. Furthermore, not only the optimization results are compared with results obtained by other multiobjective optimization methods, but also guarantee the advantage of no time-spending and complex parameter tuning.

A critical analysis on "Active Learning" in the light of Cultural-Historical Activity Theory (CHAT): Implications to Physics Education and to experimental activities as a particular case.

This is a research paper in which we discuss “active learning” in the light of Cultural-Historical Activity Theory (CHAT), a powerful framework to analyze human activity, including teaching and learning process and the relations between education and wider human dimensions as politics, development, emancipation etc. This framework has its origin in Vygotsky's works in the psychology, supported by a Marxist perspective, but nowadays is a interdisciplinary field encompassing History, Anthropology, Psychology, Education for example.

Aktionenlernen mit Selbstorganisierenden Karten und Reinforcement Learning

Die vorliegende Arbeit beschäftigt sich mit der Entwicklung eines Funktionsapproximators und dessen Verwendung in Verfahren zum Lernen von diskreten und kontinuierlichen Aktionen: 1. Ein allgemeiner Funktionsapproximator – Locally Weighted Interpolating Growing Neural Gas (LWIGNG) – wird auf Basis eines Wachsenden Neuralen Gases (GNG) entwickelt. Die topologische Nachbarschaft in der Neuronenstruktur wird verwendet, um zwischen benachbarten Neuronen zu interpolieren und durch lokale Gewichtung die Approximation zu berechnen. Die Leistungsfähigkeit des Ansatzes, insbesondere in Hinsicht auf sich verändernde Zielfunktionen und sich verändernde Eingabeverteilungen, wird in verschiedenen Experimenten unter Beweis gestellt. 2. Zum Lernen diskreter Aktionen wird das LWIGNG-Verfahren mit Q-Learning zur Q-LWIGNG-Methode verbunden. Dafür muss der zugrunde liegende GNG-Algorithmus abgeändert werden, da die Eingabedaten beim Aktionenlernen eine bestimmte Reihenfolge haben. Q-LWIGNG erzielt sehr gute Ergebnisse beim Stabbalance- und beim Mountain-Car-Problem und gute Ergebnisse beim Acrobot-Problem. 3. Zum Lernen kontinuierlicher Aktionen wird ein REINFORCE-Algorithmus mit LWIGNG zur ReinforceGNG-Methode verbunden. Dabei wird eine Actor-Critic-Architektur eingesetzt, um aus zeitverzögerten Belohnungen zu lernen. LWIGNG approximiert sowohl die Zustands-Wertefunktion als auch die Politik, die in Form von situationsabhängigen Parametern einer Normalverteilung repräsentiert wird. ReinforceGNG wird erfolgreich zum Lernen von Bewegungen für einen simulierten 2-rädrigen Roboter eingesetzt, der einen rollenden Ball unter bestimmten Bedingungen abfangen soll.

Untersuchung der Auswirkungen verschiedener Variationsbereiche des differenziellen Lernens und Lehrens im weiten Sinn auf ausgewählte technische Grundfertigkeiten im Hallenhockey

Die Frage wie großmotorische Bewegungen gelernt werden beschäftigt nicht nur Sportler, Trainer und Sportlehrer sondern auch Ärzte und Physiotherapeuten. Die sportwissenschaftlichen Teildisziplinen Bewegungs- und Trainingswissenschaft versuchen diese Frage sowohl im Sinne der Grundlagenforschung (Wie funktioniert Bewegungslernen?) als auch hinsichtlich der praktischen Konsequenzen (Wie lehrt man Bewegungen?) zu beantworten. Innerhalb dieser Themenfelder existieren Modelle, die Bewegungslernen als gezielte und extern unterstützte Ausbildung zentralnervöser Bewegungsprogramme verstehen und solche, die Lernen als Selbstorganisationsprozess interpretieren. Letzteren ist das Differenzielle Lernen und Lehren (Schöllhorn, 1999) zuzuordnen, das die Notwendigkeit betont, Bewegungen durch die Steigerung der Variationen während der Aneignungsphase zu lernen und zu lehren. Durch eine Vielzahl an Variationen, so die Modellannahme, findet der Lernende ohne externe Vorgaben selbstorganisiert ein individuelles situatives Optimum. Die vorliegende Arbeit untersucht, welchen Einfluss Variationen verschiedener Art und Größe auf die Lern- und Aneignungsleistung großmotorischer Bewegungen haben und in wie fern personenübergreifende Optima existieren. In zwei Experimenten wird der Einfluss von räumlichen (Bewegungsausführung, Bewegungsergebnis) und zeitlichen Variationen (zeitliche Verteilung der Trainingsreize) auf die Aneignungs- und Lernleistung großmotorischer sportlicher Bewegungen am Beispiel zweier technischer Grundfertigkeiten des Hallenhockeys untersucht. Die Ergebnisse der Experimente stützen die bisherige Befundlage zum Differenziellen Lernen und Lehren, wonach eine Zunahme an Variation in der Aneignungsphase zu größeren Aneignungs- und Lernleistungen führt. Zusätzlich wird die Annahme bestätigt, dass ein Zusammenhang von Variationsbereich und Lernrate in Form eines Optimaltrends vorliegt. Neu sind die Hinweise auf die Dynamik von motorischen Lernprozessen (Experiment 1). Hier scheinen individuelle Faktoren (z. B. die Lernbiografie) als auch die Phase im Lernprozess (Aneignung, Lernen) Einfluss zu haben auf den Umfang und die Struktur eines für die optimale Adaptation notwendigen Variationsbereichs. Darüber hinaus weisen die Befunde auf verschiedene Aneignungs- und Lerneffekte aufgrund alleiniger Variation der zeitlichen Verteilung bei ansonsten gleichen Trainingsreizen hin (Experiment 2). Für zukünftige Forschungsarbeiten zum Erlernen großmotorischer Bewegungen und für die sportliche Praxis dürfte es daher erkenntnisreich sein, die Historie der intrinsischen Dynamik der lernenden Systeme stärker zu berücksichtigen. Neben Fragestellungen für die Grundlagenforschung zum (Bewegungs-)Lernen ließen sich hieraus unmittelbar praxisrelevante Erkenntnisse darüber ableiten, wie Bewegungslernprozesse mittels verschiedener Variationsbereiche strukturiert und gesteuert werden könnten.

Pedagogical techniques and student outcomes in applied instrumental lessons taught by experienced and pre-service American music teachers.

The purpose of the study was to examine the effect of teacher experience on student progress and performance quality in an introductory applied lesson. Nine experienced teachers and 15 pre-service teachers taught an adult beginner to play ‘Mary Had a Little Lamb’ on a wind instrument. The lessons were videotaped for subsequent analysis of teaching behaviors and performance achievement. Following instruction, a random sample of teachers was interviewed about their perceptions of the lesson. A panel of adjudicators rated final pupil performances. No significant difference was found between pupils taught by experienced and pre-service teachers in the quality of their final performance. Systematic observation of the videotaped lessons showed that participant teachers provided relatively frequent and highly positive reinforcement during the lessons. Pupils of experienced teachers talked significantly more during the lessons than did pupils of pre-service teachers. Pre-service teachers modeled significantly more on their instruments than did experienced teachers.

Learning My Lessons: Research, Rehearsal, and Reflection on the Greats

A successful actor often requires a specific acting method or style to enhance their performance. Through theatrical research, rehearsal and performance, an actor can narrow down their seemingly endless search for the most productive methodology. By researching, studying, and applying the methods of Constantin Stanislavski, Stella Adler,and Tadashi Suzuki to my rehearsal process, I have found my most effective acting style: Stella Adler?s method. I utilize this acting method during the performance period of my early professional acting career. Experimental research for this thesis was completed inthe studio. I applied each of the three aforementioned methods to a dramatic/classical monologue. The results I gathered helped me to decide upon Adler?s methodology to carry with me through my upcoming professional auditions and career. From casting resulting from the auditions, I will employ the methodology to my professional work asan actress. Each acting teacher has provided the performance world with a new way to experience their stage time. The methods are unique and enable the actor to find the most dynamic performance through engaging technical skill.

Applied Graph Theory in Computer Vision and Pattern Recognition

This book will serve as a foundation for a variety of useful applications of graph theory to computer vision, pattern recognition, and related areas. It covers a representative set of novel graph-theoretic methods for complex computer vision and pattern recognition tasks. The first part of the book presents the application of graph theory to low-level processing of digital images such as a new method for partitioning a given image into a hierarchy of homogeneous areas using graph pyramids, or a study of the relationship between graph theory and digital topology. Part II presents graph-theoretic learning algorithms for high-level computer vision and pattern recognition applications, including a survey of graph based methodologies for pattern recognition and computer vision, a presentation of a series of computationally efficient algorithms for testing graph isomorphism and related graph matching tasks in pattern recognition and a new graph distance measure to be used for solving graph matching problems. Finally, Part III provides detailed descriptions of several applications of graph-based methods to real-world pattern recognition tasks. It includes a critical review of the main graph-based and structural methods for fingerprint classification, a new method to visualize time series of graphs, and potential applications in computer network monitoring and abnormal event detection.

Evaluating retraining rules for semi-supervised learning in neural network based cursive word recognition

Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is self-training, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer can be significantly improved through the use of unlabeled data and self-training if appropriate retraining rules are applied.

E-Learning-Webseite als facettenreiches Werkzeug in Forschung und Lehre

Im Rahmen des blended learning kann eine E-Learning-Webseite als Begleitmaterial einer Lehrveranstaltung eingesetzt werden oder Studierende zur aktiven Teilnahme an der Erstellung der Webseiteninhalte anregen. Darüber hinaus eignet sich eine solche Webseite als Plattform zur E-Learning-Forschung. Auch empirische Studien können dort eingebettet werden. Eine weitere wissenschaftliche Anwendung bietet die Analyse des Nutzerverhaltens, mit der sich aktuelle Forschungsergebnisse zum Lernen mit Hypermedien überprüfen lassen. Wir beschreiben eine solche, vielseitig einsetzbare Webseite, die eine Verknüpfung von universitärer Lehre und Forschung ermöglicht und als Anregung für ähnliche Projekte dienen kann. Erste Erfahrungen werden dabei berichtet und ausgewählte Empfehlungen für Dozierende und Forscher abgeleitet.

Learning Two-Person Interaction Models for Responsive Synthetic Humanoids

Imitation learning is a promising approach for generating life-like behaviors of virtual humans and humanoid robots. So far, however, imitation learning has been mostly restricted to single agent settings where observed motions are adapted to new environment conditions but not to the dynamic behavior of interaction partners. In this paper, we introduce a new imitation learning approach that is based on the simultaneous motion capture of two human interaction partners. From the observed interactions, low-dimensional motion models are extracted and a mapping between these motion models is learned. This interaction model allows the real-time generation of agent behaviors that are responsive to the body movements of an interaction partner. The interaction model can be applied both to the animation of virtual characters as well as to the behavior generation for humanoid robots.