A hybrid training method for B-spline neural networks

Current and past research has brought up new views related to the optimization of neural networks. For a fixed structure, second order methods are seen as the most promising. From previous works we have shown how second order methods are of easy applicability to a neural network. Namely, we have proved how the Levenberg-Marquard possesses not only better convergence but how it can assure the convergence to a local minima. However, as any gradient-based method, the results obtained depend on the startup point. In this work, a reformulated Evolutionary algorithm - the Bacterial Programming for Levenberg-Marquardt is proposed, as an heuristic which can be used to determine the most suitable starting points, therefore achieving, in most cases, the global optimum.

Completely supervised training algorithms for B-spline neural networks and neuro-fuzzy systems

Complete supervised training algorithms for B-spline neural networks and fuzzy rule-based systems are discussed. By interducing the relationship between B-spline neural networks and certain types of fuzzy models, training algorithms developed initially for neural networks can be adapted by fuzzy systems.

Training multilayer perceptrons - an optimization perspective

Multilayer perceptrons (MLPs) (1) are the most common artificial neural networks employed in a large field of applications. In control and signal processing applications, MLPs are mainly used as nonlinear mapping approximators. The most common training algorithm used with MLPs is the error back-propagation (BP) alg. (1).

Training multilayer perceptrons for control systems applications - a comparison of different approaches

Multilayer perceptrons (MLPs) (1) are the most common artificial neural networks employed in a large field of applications. In control and signal processing applications, MLPs are mainly used as nonlinear mapping approximators. The most common training algorithm used with MLPs is the error back-propagation (BP) alg. (1).

Supervised training approach using spiking neural networks

One of the basic aspects of some neural networks is their attempt to approximate as much as possible their biological counterparts. The goal is to achieve a simple and robust network, easy to understand and able of simulating the human brain at a computational level. Recently a third generation of neural networks (NN) [1], called Spiking Neural Networks(SNN) was appeared. This new kind of networks use the time of a electrical pulse, or spike, to encode the information. In the first and second generation of NN analog values are used in the communication between neurons.

Training neuro-fuzzy models using evolution based algorithms

The normal design process for neural networks or fuzzy systems involve two different phases: the determination of the best topology, which can be seen as a system identification problem, and the determination of its parameters, which can be envisaged as a parameter estimation problem. This latter issue, the determination of the model parameters (linear weights and interior knots) is the simplest task and is usually solved using gradient or hybrid schemes. The former issue, the topology determination, is an extremely complex task, especially if dealing with real-world problems.

Radiographers perceptions of magnetic resonance imaging: a study of the causes that lead to the exams repetition

Purpose: To know how often occur the repetitions of MRI exams and sequences in radiology departments. Methods and Materials: A self applied-questionnaire was used as instrument and assigned to 57 radiographers who performed MRI exams to determine which were the causes that lead to the repetition. The questionnaires were interpreted and statistically analyzed through descriptive statistics and Spearman’s rho correlations. Results: At a 95% confidence interval, the major results suggest that the patient’s movement during de MRI exams is the main cause to repeat this exams (mean of 3.88 on a 5 points likert scale). However, there are causes related to the radiographer’s and the results showed that the introduction of wrong imaging parameters by the performer are a major cause too (N=26). Spearman rho correlations between radiographer’s time of experience and frequency of MRI exams repetitions were poor and not significant (r=0.141; p=0.297). The correlations between radiographer’s tiredness and frequency of MRI exams repetitions were negative, weak and not significant (r= -0.151; p=0.263). Conclusion: The patients’ movement may disrupt the examination or degrade the images with artifacts. The level of experience doesn’t influence the repetitions of MRI exams, it seems that seniors radiographers don’t have improvements in performance as it should be expected. It’s recommendable to do training courses regularly to improve the performance and systematically evaluate. Several features will need to be identified which would decrease the MRI exams repetitions.

virtX - Ein rechnergestütztes System zum Training des intraoperativen Einsatzes eines mobilen Bildverstärkers

Hintergrund und Fragestellung: Die korrekte intraoperative Positionierung und Einstellung eines mobilen Bildverstärkers (auch C-Bogen) kann zurzeit theoretisch mit Hilfe von Lehrbüchern erlernt, am Gerät selbst aber nur ohne visuelle Rückmeldung, d.h. ohne ein zur Ausrichtung korrespondierendes Röntgenbild, trainiert werden. Hieraus ergibt sich die Fragestellung, inwiefern das Training der Handhabung und richtigen Einstellung des C-Bogens in verschiedenen Operationsszenarien durch ein C-Bogen Simulationssystem als Teil eines CBT-Systems (Computer Based Training) unterstützt werden kann. Methoden: In Kooperation mit Ärzten aus Unfallchirurgie und Radiologie wurde das computer-basierte Trainingssystem virtX entwickelt. virtX kann dem Nutzer verschiedene Aufgaben zur Einstellung eines C-Bogens stellen und die Ausführung und das Ergebnis bewerten. Die Aufgaben können mit Hilfe eines Autorensystems erstellt und vom Trainierenden in verschiedenen Modi erfüllt werden: im rein virtuellen Modus oder im kombinierten virtuell-realen Modus. Im rein virtuellen Modus steuert der Nutzer den virtuellen C-Bogen in einem virtuellen OP-Saal mittels einer grafisch-interaktiven Benutzungsoberfläche. Im virtuell-realen Modus hingegen wird die Ausrichtung eines realen C-Bogens erfasst und auf den virtuellen C-Bogen übertragen. Während der Aufgabenerfüllung kann der Benutzer zu jeder Zeit ein realitätsnahes, virtuelles Röntgenbild erzeugen und dabei alle Parameter wie Blendenstellung, Röntgenintensität, etc. wie bei einem realen C-Bogen steuern. virtX wurde auf einem dreitägigen Kurs für OP-Personal mit 120 Teilnehmern eingesetzt und auf der Basis von Fragebögen evaluiert. Ergebnisse: Von den Teilnehmern gaben 79 einen ausgefüllten Evaluations-Fragebogen ab. Das Durchschnittsalter der 62 weiblichen und 15 männlichen Teilnehmer (zwei o.A.) lag bei 34 ± 9 Jahren, die Berufserfahrung bei 8,3 ± 7,6 Jahren. 18 Personen (23%) gaben an, gelegentlich mit einem C-Bogen zu arbeiten, 61 (77%) arbeiteten regelmäßig damit. Über 83% der befragten Teilnehmer empfanden virtX als eine sinnvolle Ergänzung zur herkömmlichen Ausbildung am C-Bogen. Das virtuelle Röntgen wurde mit einer Zustimmung von 91% der befragten Teilnehmer als besonders wichtig für das Verständnis der Arbeitsweise eines C-Bogens beurteilt. Ebenso erhielt der kombinierte virtuell-reale Modus mit 84% Zustimmung einen vergleichsweise hohen Stellenwert. Schlussfolgerung: Die Befragung zeichnet ein positives Bild der Akzeptanz des virtX-System als substanzielle Ergänzung zur herkömmlichen Ausbildung am C-Bogen.

S.C. Recycling Professionals Certification Training Manual 2015

The certification program is centered on a three-day workshop that includes detailed instruction and a 16-chapter manual/reference guide. The manual/reference guide offers a comprehensive overview of both old and new recycling issues faced by programs including composting, electronics and funding. It also provides detailed information on the requirements of county programs as outlined in the S.C. Solid Waste Policy and Management Act of 1991.

ILS and RTP: Support to Researchers Provided by Information and Learning Services as Part of the Research Training Programme at the University of Worcester, Past, Present and Future.

The purpose of this article is to investigate the involvement of Information and Learning Services staff in the delivery of the Research Training Programme at the University of Worcester, UK with a focus on researcher receptivity. I believe that by constantly reflecting on the development of that part of the programme delivered by ILS and by examining feedback from the sessions, it is possible to improve and increase the level of researcher receptivity. It is hoped that such examination and reflection will be of value and relevance to the IL community since by reflecting on success and failure in a local context and by mapping this reflection to existing research enables librarians to improve the support provided to researchers within their institutions. This article outlines the support given to research students at the University of Worcester in the past, examines the changes leading to present programme delivery and reflects on considerations for future support. The article is underpinned by reference to current research undertaken in international (albeit Western-centric) contexts. I note that the rationale behind changes is embedded in current adult learning and teaching theory. In an increasingly competitive research environment where funding is dependent on a statistically monitored research output, the aim of such support is to integrate any IL contribution into the wider research training programme. Thus resource discovery becomes part of the reflexive research cycle. Implicit in this investigative reflection is the desire of the IL community to constantly strive towards the positive reception of IL into research support programmes which are perceived by researchers as highly valuable to the process and progress of their work.

The challenges of integrating the discussion of controversial issues in initial teacher training

In the framework of the Bologna process, and with regard to pre-service teacher education, it is necessary to model student-centred learning experiences in order to promote the required competences for future professional practice and critical participation in society. Despite the potential of discussion in promoting several competences, this methodology does not always integrate the teaching practices. This case study sought to: a) understand the experiences and views of future teachers from a School of Education on the use of discussion in their past education; and b) investigate the impact of an educational experience centred on discussion. Data were collected through narratives, questionnaires, interviews and participant observation. The learning situations experienced through this study contributed to the development of citizens more aware of their role in society and allowed the promotion of skills indispensable for an Elementary Education teacher.

Training the public health workforce we need. Exploring perceptions for future public heath workers in Ecuador

Thesis (Master's)--University of Washington, 2015

From engagement to outcomes: measuring the impact of researcher training using the rugby team impact framework

This study addresses our approach to the difficult task of measuring the impact of an eLearning service, the Graduate Virtual Research Environment (GVRE), provided to doctoral students at a UK University since October 2009. The GVRE provides research students with access to a training needs analysis tool which is linked to a repository of video learning resources created by academics and experienced research students. This paper explores the use of the Rugby Team Impact Framework as a guide to measuring impact and our use of a number of techniques to gather evidence about the changes resulting from use of the GVRE. The framework gives four levels of evidence, starting with simple measures of provision, through attendance, interest and to outcomes. As with other research, we found the former easy to assess but the outcomes harder to define. We conclude with a critical evaluation of our research process and outcomes.