George Magoulas | Birkbeck College, University of London (original) (raw)

Uploads

Papers by George Magoulas

Research paper thumbnail of Distillation of Deep Learning Ensembles as a Regularisation Method

Smart innovation, systems and technologies, Oct 15, 2017

Research paper thumbnail of Transfer Learning and Magnetic Resonance Imaging Techniques for the Deep Neural Network-Based Diagnosis of Early Cognitive Decline and Dementia

Research paper thumbnail of Predicting Seriousness of Injury in a Traffic Accident: A New Imbalanced Dataset and Benchmark

arXiv (Cornell University), May 20, 2022

Research paper thumbnail of Initialising Deep Neural Networks: An Approach Based on Linear Interval Tolerance

Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016, 2017

Deep neural networks, supported by recent advances in hardware and the availability of computatio... more Deep neural networks, supported by recent advances in hardware and the availability of computational resources, have managed to outperform multilayer neural networks, with one or two hidden layers, producing impressive results in several difficult tasks. Nevertheless, training deep networks remains considerably challenging and there is lack of approaches for initialising deep architectures. In this paper we present an approach that builds on interval analysis to provide weight initialisation for deep neural networks. We have built on our previous work presented in [1], making the necessary adjustments to tailor for deeper architectures. We conducted an empirical study to preliminary evaluate this approach using well known benchmarks from the deep learning literature.

Research paper thumbnail of Deep Learning of Brain Asymmetry Images and Transfer Learning for Early Diagnosis of Dementia

Proceedings of the International Neural Networks Society, 2021

Research paper thumbnail of User model interoperability in education: sharing learner datausing the experience API and distributed ledger technology

Learning analytics and data mining require gathering and exchanging learner data for further proc... more Learning analytics and data mining require gathering and exchanging learner data for further processing and designing of activities tailored to learner’s characteristics, context, and needs. Currently, systems that store learners’ attributes should, ideally, be operated and controlled by responsible and trustworthy authorities that guarantee the protection and sovereignty of data and use objective criteria to protect and represent all parties’ interests. This chapter introduces a peer-to-peer method for storing and exchanging learner data with minimal trust. The proposed approach, underpinned by the Experience API standard, eliminates the need of a mediator authority by using distributed ledger technology.

Research paper thumbnail of Creating Ensembles of Generative Adversarial Network Discriminators for One-Class Classification

Proceedings of the International Neural Networks Society, 2021

Research paper thumbnail of The Pedagogy of Things : Emerging Models of Experiential Learning

The emergence of ubiquitous computing technologies have made the once theorized “Internet of thin... more The emergence of ubiquitous computing technologies have made the once theorized “Internet of things” a reality, and this quickly evolving technological infrastructure, in conjunction with a variety of mobile devices, including smartphones and tablets, is providing incredibly rich opportunities for learning. This article provides a description of these technological innovations and posits experiential learning as a key pedagogical strategy that is likely to benefit most from these technologies. It also provides examples of this new pedagogy of things, a pedagogy that embraces the emerging technological attributes of the real world around us.

Research paper thumbnail of Computational Approaches to Artificial Intelligence: Theory, Methods and Applications

International Conference of Computational Methods in Sciences and Engineering 2004 (ICCMSE 2004), 2019

Research paper thumbnail of Users’ perceptions of e-learning environments and services effectiveness

Journal of Enterprise Information Management, 2018

Purpose E-learning environments and services (ELES) adoption and success rates challenge ELES des... more Purpose E-learning environments and services (ELES) adoption and success rates challenge ELES designers, practitioners and organisations. Enterprise decision makers continue to seek effective instruments in launching such systems. The purpose of this paper is to understand users’ perceptions of ELES effectiveness and develop a theoretical framework which improves understanding of success factors for adoption. Design/methodology/approach Grounded theory method is used to reflect on the relationships between changing users’ requirements and expectations, technological advances and ELES effectiveness models. A longitudinal study collecting data from social media blogs over four years was authenticated based on the context evaluation, language structure and conversational constructs. Findings Identification of a new core dimension named “Concept Functionality” which can be used to understand the relationships between e-learning effectiveness factors including the relationships with othe...

Research paper thumbnail of The cloudUPDRS app: A medical device for the clinical assessment of Parkinson’s Disease

Pervasive and Mobile Computing, 2018

Research paper thumbnail of A Review, Timeline, and Categorization of Learning Design Tools

Lecture Notes in Computer Science, 2016

Research paper thumbnail of Libe Project – Supporting Lifelong Learning with Inquiry-Based Education

Research paper thumbnail of Model-based design and evaluation of interactive applications

European Journal of Information Systems, 2001

Research paper thumbnail of Design and Evaluation of a Case-Based System for Modelling Exploratory Learning Behavior of Math Generalization

IEEE Transactions on Learning Technologies, 2017

Research paper thumbnail of Synthesizing Technological and Pedagogical Knowledge in Learning Design

International Journal of Digital Literacy and Digital Competence, 2016

Based on a design rational for constructivist pre-service teacher training on Technology Enhanced... more Based on a design rational for constructivist pre-service teacher training on Technology Enhanced Learning (TEL), in this paper the authors consider teachers as designers of innovative digital educational content. Under this lens, the selection of appropriate technologies is considered as a threefold process that concerns the availability of technological tools for implementing a virtual classroom that facilitates communication, collaboration, and administration, the enabling technologies for serving specific learning purposes, and the technologies or tools that support trainees to design effective TEL-based courses. A number of questions emerge as the authors are looking for the most appropriate technologies for cultivating certain competences related to class operation, learning design and student engagement in a constructive manner. As a first step, in this paper, they investigate how trainees combine particular technologies with pedagogical tools to cultivate specific competence...

Research paper thumbnail of Customised ensemble methodologies for deep learning: Boosted Residual Networks and related approaches

Neural Computing and Applications, 2018

Research paper thumbnail of Neural adaptive admission control framework: SLA-driven action termination for real-time application service management

Enterprise Information Systems, 2019

Research paper thumbnail of Teachers' Perspectives on Design for Learning using Computer based Information Systems: a Systematic literature Review

Research paper thumbnail of An Eco-Friendly Intelligent Environment for Exploring Mathematical Generalisation

Artificial Intelligence in Education, 2009

Richard Noss, Celia Hoyles, Manolis Mavrikis, Eirini Geraniou, Sergio Gutierrez-Santos, and Darre... more Richard Noss, Celia Hoyles, Manolis Mavrikis, Eirini Geraniou, Sergio Gutierrez-Santos, and Darren Pearce. Broadening the sense of 'dynamic': a microworld to support students' mathematical generalisation. Special Issue of The International Journal on Mathematics Education (ZDM): Transforming Mathematics Education through the Use of Dynamic Mathematics Technologies, 41(5), 2009. To appear. ... Eirini Geraniou, Manolis Mavrikis, Richard Noss, and Celia Hoyles. A learning environment to support mathematical generalisation in the ...

Research paper thumbnail of Distillation of Deep Learning Ensembles as a Regularisation Method

Smart innovation, systems and technologies, Oct 15, 2017

Research paper thumbnail of Transfer Learning and Magnetic Resonance Imaging Techniques for the Deep Neural Network-Based Diagnosis of Early Cognitive Decline and Dementia

Research paper thumbnail of Predicting Seriousness of Injury in a Traffic Accident: A New Imbalanced Dataset and Benchmark

arXiv (Cornell University), May 20, 2022

Research paper thumbnail of Initialising Deep Neural Networks: An Approach Based on Linear Interval Tolerance

Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016, 2017

Deep neural networks, supported by recent advances in hardware and the availability of computatio... more Deep neural networks, supported by recent advances in hardware and the availability of computational resources, have managed to outperform multilayer neural networks, with one or two hidden layers, producing impressive results in several difficult tasks. Nevertheless, training deep networks remains considerably challenging and there is lack of approaches for initialising deep architectures. In this paper we present an approach that builds on interval analysis to provide weight initialisation for deep neural networks. We have built on our previous work presented in [1], making the necessary adjustments to tailor for deeper architectures. We conducted an empirical study to preliminary evaluate this approach using well known benchmarks from the deep learning literature.

Research paper thumbnail of Deep Learning of Brain Asymmetry Images and Transfer Learning for Early Diagnosis of Dementia

Proceedings of the International Neural Networks Society, 2021

Research paper thumbnail of User model interoperability in education: sharing learner datausing the experience API and distributed ledger technology

Learning analytics and data mining require gathering and exchanging learner data for further proc... more Learning analytics and data mining require gathering and exchanging learner data for further processing and designing of activities tailored to learner’s characteristics, context, and needs. Currently, systems that store learners’ attributes should, ideally, be operated and controlled by responsible and trustworthy authorities that guarantee the protection and sovereignty of data and use objective criteria to protect and represent all parties’ interests. This chapter introduces a peer-to-peer method for storing and exchanging learner data with minimal trust. The proposed approach, underpinned by the Experience API standard, eliminates the need of a mediator authority by using distributed ledger technology.

Research paper thumbnail of Creating Ensembles of Generative Adversarial Network Discriminators for One-Class Classification

Proceedings of the International Neural Networks Society, 2021

Research paper thumbnail of The Pedagogy of Things : Emerging Models of Experiential Learning

The emergence of ubiquitous computing technologies have made the once theorized “Internet of thin... more The emergence of ubiquitous computing technologies have made the once theorized “Internet of things” a reality, and this quickly evolving technological infrastructure, in conjunction with a variety of mobile devices, including smartphones and tablets, is providing incredibly rich opportunities for learning. This article provides a description of these technological innovations and posits experiential learning as a key pedagogical strategy that is likely to benefit most from these technologies. It also provides examples of this new pedagogy of things, a pedagogy that embraces the emerging technological attributes of the real world around us.

Research paper thumbnail of Computational Approaches to Artificial Intelligence: Theory, Methods and Applications

International Conference of Computational Methods in Sciences and Engineering 2004 (ICCMSE 2004), 2019

Research paper thumbnail of Users’ perceptions of e-learning environments and services effectiveness

Journal of Enterprise Information Management, 2018

Purpose E-learning environments and services (ELES) adoption and success rates challenge ELES des... more Purpose E-learning environments and services (ELES) adoption and success rates challenge ELES designers, practitioners and organisations. Enterprise decision makers continue to seek effective instruments in launching such systems. The purpose of this paper is to understand users’ perceptions of ELES effectiveness and develop a theoretical framework which improves understanding of success factors for adoption. Design/methodology/approach Grounded theory method is used to reflect on the relationships between changing users’ requirements and expectations, technological advances and ELES effectiveness models. A longitudinal study collecting data from social media blogs over four years was authenticated based on the context evaluation, language structure and conversational constructs. Findings Identification of a new core dimension named “Concept Functionality” which can be used to understand the relationships between e-learning effectiveness factors including the relationships with othe...

Research paper thumbnail of The cloudUPDRS app: A medical device for the clinical assessment of Parkinson’s Disease

Pervasive and Mobile Computing, 2018

Research paper thumbnail of A Review, Timeline, and Categorization of Learning Design Tools

Lecture Notes in Computer Science, 2016

Research paper thumbnail of Libe Project – Supporting Lifelong Learning with Inquiry-Based Education

Research paper thumbnail of Model-based design and evaluation of interactive applications

European Journal of Information Systems, 2001

Research paper thumbnail of Design and Evaluation of a Case-Based System for Modelling Exploratory Learning Behavior of Math Generalization

IEEE Transactions on Learning Technologies, 2017

Research paper thumbnail of Synthesizing Technological and Pedagogical Knowledge in Learning Design

International Journal of Digital Literacy and Digital Competence, 2016

Based on a design rational for constructivist pre-service teacher training on Technology Enhanced... more Based on a design rational for constructivist pre-service teacher training on Technology Enhanced Learning (TEL), in this paper the authors consider teachers as designers of innovative digital educational content. Under this lens, the selection of appropriate technologies is considered as a threefold process that concerns the availability of technological tools for implementing a virtual classroom that facilitates communication, collaboration, and administration, the enabling technologies for serving specific learning purposes, and the technologies or tools that support trainees to design effective TEL-based courses. A number of questions emerge as the authors are looking for the most appropriate technologies for cultivating certain competences related to class operation, learning design and student engagement in a constructive manner. As a first step, in this paper, they investigate how trainees combine particular technologies with pedagogical tools to cultivate specific competence...

Research paper thumbnail of Customised ensemble methodologies for deep learning: Boosted Residual Networks and related approaches

Neural Computing and Applications, 2018

Research paper thumbnail of Neural adaptive admission control framework: SLA-driven action termination for real-time application service management

Enterprise Information Systems, 2019

Research paper thumbnail of Teachers' Perspectives on Design for Learning using Computer based Information Systems: a Systematic literature Review

Research paper thumbnail of An Eco-Friendly Intelligent Environment for Exploring Mathematical Generalisation

Artificial Intelligence in Education, 2009

Richard Noss, Celia Hoyles, Manolis Mavrikis, Eirini Geraniou, Sergio Gutierrez-Santos, and Darre... more Richard Noss, Celia Hoyles, Manolis Mavrikis, Eirini Geraniou, Sergio Gutierrez-Santos, and Darren Pearce. Broadening the sense of 'dynamic': a microworld to support students' mathematical generalisation. Special Issue of The International Journal on Mathematics Education (ZDM): Transforming Mathematics Education through the Use of Dynamic Mathematics Technologies, 41(5), 2009. To appear. ... Eirini Geraniou, Manolis Mavrikis, Richard Noss, and Celia Hoyles. A learning environment to support mathematical generalisation in the ...