- George D. Magoulas
- London, United Kingdom
- I am Professor of Computer Science and Director of Teaching Quality in Birkbeck’s Department of Computer Science and Information Systems, and Co-Director of the Birkbeck Knowledge Lab. I am Fellow of the Advance HE, and Member of the EPSRC College, UK. I hold BEng/MEng and Dr. Eng (University of Patras, Greece) and PGCE(HE) (Brunel University, UK). Before becoming an academic, I held R&D positions in the cement and automotive industries designing fuzzy and neural components for embedded systems. My team designs and develops innovative learning algorithms and system components that employ machine learning and deep networks, sometimes combined with symbolic AI, for psychophysiological data modelling and classification, and intelligent learning environments. The aim is to enable systems to exhibit different levels of intelligence, learn from data and transfer knowledge to new contexts. Our work has received best paper awards by the IEEE (2000 and 2008), the European Network on Intelligent Technologies for Smart Adaptive Systems (2001 and 2004), the International Association for Development of the Information Society (2006), the ACM (2009) and KES International (2010).
8 Oct 2016
New papers
Deep Incremental Boosting at GCAI 2016.
Learning Input Features Representations in Deep Learning
Regularizing Deep Learning Ensembles by Distillation at ECAI's CIMA 2016.
Bounding the Search Space for Global Optimization of Neural Networks Learning Error: An Interval Analysis Approach in JMLR.
A Review, Timeline, and Categorization of Learning Design Tools at ICWL 2016; shortlisted for the ICWL 2016 best paper award.
Approaches to Design for Learning at ICWL 2016.
An Architecture for Smart Lifelong Learning Design at ICSLE 2016.
Ubiquitous Learning Architecture to Enable Learning Path Design across the Cumulative Learning Continuum, in Informatics.
