scispace - formally typeset
G

George D. Magoulas

Researcher at Birkbeck, University of London

Publications -  241
Citations -  5380

George D. Magoulas is an academic researcher from Birkbeck, University of London. The author has contributed to research in topics: Artificial neural network & Deep learning. The author has an hindex of 35, co-authored 234 publications receiving 5068 citations. Previous affiliations of George D. Magoulas include Institute of Education & University of Patras.

Papers
More filters
Journal ArticleDOI

Personalizing the Interaction in a Web-based Educational Hypermedia System: the case of INSPIRE

TL;DR: The aim of INSPIRE is to make a shift towards a more 'learning-focused' paradigm of instruction by providing a sequence of authentic and meaningful tasks that matches learner' preferred way of studying.
Journal ArticleDOI

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

TL;DR: 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, and presents the findings of the study.
Journal ArticleDOI

Effective backpropagation training with variable stepsize

TL;DR: Backpropagation training is based on a modified steepest descent method which allows variable stepsize and is computationally efficient and posseses interesting convergence properties utilizing estimates of the Lipschitz constant without any additional computational cost.
Journal ArticleDOI

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

TL;DR: This article focuses on gradient-based backpropagation algorithms that use either a common adaptive learning rate for all weights or an individual adaptivelearning rate for each weight and apply the Goldstein/Armijo line search.
Journal ArticleDOI

A constructionist learning environment for teachers to model learning designs

TL;DR: The case for a learning design support environment to support and scaffold teachers' engagement with and development of technology-enhanced learning, based on user requirements and on pedagogic theory is made.