George D. Magoulas

Learning as immersive experiences: Using the four-dimensional framework for designing and evaluating immersive learning experiences in a virtual world

Traditional approaches to learning have often focused upon knowledge transfer strategies that have centred on textually-based engagements with learners, and dialogic methods of interaction with tutors. The use of virtual worlds, with text-based, voice-based and a feeling of ‘presence’ naturally is allowing for more complex social interactions and designed learning experiences and role plays, as well as encouraging learner empowerment through increased interactivity. To unpick these complex social interactions and more interactive designed experiences, this paper considers the use of virtual worlds in relation to structured learning activities for college and lifelong learners. This consideration necessarily has implications upon learning theories adopted and practices taken up, with real implications for tutors and learners alike. Alongside this is the notion of learning as an ongoing set of processes mediated via social interactions and experiential learning circumstances within designed virtual and hybrid spaces. This implies the need for new methodologies for evaluating the efficacy, benefits and challenges of learning in these new ways. Towards this aim, this paper proposes an evaluation methodology for supporting the development of specified learning activities in virtual worlds, based upon inductive methods and augmented by the four-dimensional framework reported in a previous study. The study undertaken aimed to test the efficacy of the proposed evaluation methodology and framework, and to evaluate the broader uses of a virtual world for supporting lifelong learners specifically in their educational choices and career decisions. The paper presents the findings of the study and considers that virtual worlds are reorganising significantly how we relate to the design and delivery of learning. This is opening up a transition in learning predicated upon the notion of learning design through the lens of ‘immersive learning experiences’ rather than sets of knowledge to be transferred between tutor and learner. The challenges that remain for tutors rest with the design and delivery of these activities and experiences. The approach advocated here builds upon an incremental testing and evaluation of virtual world learning experiences.

Effective backpropagation training with variable stepsize

The issue of variable stepsize in the backpropagation training algorithm has been widely investigated and several techniques employing heuristic factors have been suggested to improve training time and reduce convergence to local minima. In this contribution, backpropagation training is based on a modified steepest descent method which allows variable stepsize. It is computationally efficient and posseses interesting convergence properties utilizing estimates of the Lipschitz constant without any additional computational cost. The algorithm has been implemented and tested on several problems and the results have been very satisfactory. Numerical evidence shows that the method is robust with good average performance on many classes of problems. Copyright 1996 Elsevier Science Ltd.

Towards new forms of knowledge communication: the adaptive dimension of a web-based learning environment

Adaptive Educational Hypermedia Systems aim to increase the functionality of hypermedia by making it personalised to individual learners. The adaptive dimension of these systems mainly supports knowledge communication between the system and the learner by adapting the content or the appearance of hypermedia to the knowledge level, goals and other characteristics of each learner. The main objectives are to protect learners from cognitive overload and disorientation by supporting them to find the most relevant content and path in the hyperspace. In the approach presented in this paper, learners’ knowledge level and individual traits are used as valuable information to represent learners’ current state and personalise the educational system accordingly, in order to facilitate learners to achieve their personal learning goals and objectives. Learners’ knowledge level is approached through a qualitative model of the level of performance that learners exhibit with respect to the concepts they study and is used to adapt the lesson contents and the navigation support. Learners’ individual traits and especially their learning style represent the way learners perceive and process information, and are exploited to adapt the presentation of the educational material of a lesson. The proposed approach has been implemented through various adaptation technologies and incorporated into a prototype hypermedia system. Finally, a pilot study has been conducted to investigate system’s educational effectiveness. # 2002 Elsevier Science Ltd. All rights reserved.

INSPIRE: An INtelligent System for Personalized Instruction in a Remote Environment

In this paper we present the architecture of an Adaptive Educational Hypermedia System, named INSPIRE. This particular system, throughout its interaction with the learner, dynamically generates lessons that gradually lead to the accomplishment of the learning goals selected by the learner. The lessons are generated according to the learners knowledge level, learning style and follow his/her progress. The adaptive behavior of the system, the functionality of the various modules and the opportunities offered to learners for intervention are presented.

Improving the convergence of the backpropagation algorithm using learning rate adaptation methods

This article focuses on gradient-based backpropagation algorithms that use either a common adaptive learning rate for all weights or an individual adaptive learning rate for each weight and apply the Goldstein/Armijo line search. The learning-rate adaptation is based on descent techniques and estimates of the local Lipschitz constant that are obtained without additional error function and gradient evaluations. The proposed algorithms improve the backpropagation training in terms of both convergence rate and convergence characteristics, such as stable learning and robustness to oscillations. Simulations are conducted to compare and evaluate the convergence behavior of these gradient-based training algorithms with several popular training methods.

A class of gradient unconstrained minimization algorithms with adaptive stepsize

In this paper the development, convergence theory and numerical testing of a class of gradient unconstrained minimization algorithms with adaptive stepsize are presented. The proposed class comprises four algorithms: the first two incorporate techniques for the adaptation of a common stepsize for all coordinate directions and the other two allow an individual adaptive stepsize along each coordinate direction. All the algorithms are computationally efficient and possess interesting convergence properties utilizing estimates of the Lipschitz constant that are obtained without additional function or gradient evaluations. The algorithms have been implemented and tested on some well-known test cases as well as on real-life artificial neural network applications and the results have been very satisfactory.

Adaptive Web-Based Learning: Accommodating Individual Differences through System's Adaptation.

The idea of developing educational hypermedia systems for the Web is very challenging, and demands the synergy of computer science and instructional science. The paper builds on theories from instructional design and learning styles to develop a design rational and guidelines for adaptive web-based learning systems that use individual differences as a basis of systems adaptation. Various examples are provided to illustrate how instructional manipulations with regards to content adaptation and presentation, and adaptive navigation support, as well as the overall degree of system adaptation, are guided by educational experiences geared towards individual differences.

Modeling human behavior in user-adaptive systems: Recent advances using soft computing techniques

Adaptive Hypermedia systems are becoming more important in our everyday activities and users are expecting more intelligent services from them. The key element of a generic adaptive hypermedia system is the user model. Traditional machine learning techniques used to create user models are usually too rigid to capture the inherent uncertainty of human behavior. In this context, soft computing techniques can be used to handle and process human uncertainty and to simulate human decision-making. This paper examines how soft computing techniques, including fuzzy logic, neural networks, genetic algorithms, fuzzy clustering and neuro-fuzzy systems, have been used, alone or in combination with other machine learning techniques, for user modeling from 1999 to 2004. For each technique, its main applications, limitations and future directions for user modeling are presented. The paper also presents guidelines that show which soft computing techniques should be used according to the task implemented by the application.

New globally convergent training scheme based on the resilient propagation algorithm

In this paper, a new globally convergent modification of the Resilient Propagation-Rprop algorithm is presented. This new addition to the Rprop family of methods builds on a mathematical framework for the convergence analysis that ensures that the adaptive local learning rates of the Rprops schedule generate a descent search direction at each iteration. Simulation results in six problems of the PROBEN1 benchmark collection show that the globally convergent modification of the Rprop algorithm exhibits improved learning speed, and compares favorably against the original Rprop and the Improved Rprop, a recently proposed Rrpop modification.

Neural network-based colonoscopic diagnosis using on-line learning and differential evolution

In this paper, on-line training of neural networks is investigated in the context of computer-assisted colonoscopic diagnosis. A memory-based adaptation of the learning rate for the on-line back-propagation (BP) is proposed and used to seed an on-line evolution process that applies a differential evolution (DE) strategy to (re-) adapt the neural network to modified environmental conditions. Our approach looks at on-line training from the perspective of tracking the changing location of an approximate solution of a pattern-based, and thus, dynamically changing, error function. The proposed hybrid strategy is compared with other standard training methods that have traditionally been used for training neural networks off-line. Results in interpreting colonoscopy images and frames of video sequences are promising and suggest that networks trained with this strategy detect malignant regions of interest with accuracy.