| Deep Incremental Boosting A Mosca, GD Magoulas GCAI 2016. 2nd Global Conference on Artificial Intelligence 41, 293-302, 2016 | 40 | 2016 |
| Adapting Resilient Propagation for Deep Learning A Mosca, GD Magoulas UK Workshop on Computational Intelligence, 2015 | 27 | 2015 |
| Tweedie moment projected diffusions for inverse problems B Boys, M Girolami, J Pidstrigach, S Reich, A Mosca, OD Akyildiz arXiv preprint arXiv:2310.06721, 2023 | 15 | 2023 |
| Distillation of deep learning ensembles as a regularisation method A Mosca, GD Magoulas Advances in Hybridization of Intelligent Methods: Models, Systems and …, 2018 | 7 | 2018 |
| Customised ensemble methodologies for deep learning: Boosted Residual Networks and related approaches A Mosca, GD Magoulas Neural Computing and Applications 31, 1713-1731, 2019 | 6 | 2019 |
| Boosted residual networks A Mosca, GD Magoulas Engineering Applications of Neural Networks: 18th International Conference …, 2017 | 6 | 2017 |
| Training Convolutional Networks with Weight–wise Adaptive Learning Rates A Mosca, GD Magoulas European Symposium on Artificial Neural Networks, Computational Intelligence …, 2017 | 5 | 2017 |
| On Forecasting Project Activity Durations with Neural Networks P Zachares, V Hovhannisyan, C Ledezma, J Gante, A Mosca International Conference on Engineering Applications of Neural Networks, 103-114, 2022 | 4 | 2022 |
| A hybrid model for forecasting short-term electricity demand ME Athanasopoulou, J Deveikyte, A Mosca, I Peri, A Provetti Proceedings of the Second ACM International Conference on AI in Finance, 1-6, 2021 | 4 | 2021 |
| Hardening against adversarial examples with the smooth gradient method A Mosca, GD Magoulas Soft Computing, 2018 | 4 | 2018 |
| Regularizing deep learning ensembles by distillation A Mosca, GD Magoulas 6th international workshop on combinations of intelligent methods and …, 2016 | 4 | 2016 |
| Extending Encog: a study on classifier ensemble techniques A Mosca Birkbeck, University of London, 2012 | 3 | 2012 |
| Data-Driven Schedule Risk Forecasting for Construction Mega-Projects V Hovhannisyan, P Zachares, Y Grushka-Cockayne, A Mosca, ... Available at SSRN 4496119, 2023 | 2 | 2023 |
| How to calibrate your neural network classifier: getting true probabilities from a classification model N Culakova, D Murphy, J Gante, C Ledezma, V Hovhannisyan, A Mosca Proceedings of the 26th ACM SIGKDD International Conference on Knowledge …, 2020 | 2 | 2020 |
| Form follows Function: Text-to-Text Conditional Graph Generation based on Functional Requirements PA Zachares, V Hovhannisyan, A Mosca, Y Gal arXiv preprint arXiv:2311.00444, 2023 | 1 | 2023 |
| Learning Input Features Representations in Deep Learning A Mosca, GD Magoulas Advances in Computational Intelligence Systems: Contributions Presented at …, 2017 | 1 | 2017 |
| A Hybrid Model for Forecasting Short-Term Electricity Demand M Eleni Athanasopoulou, J Deveikyte, A Mosca, I Peri, A Provetti arXiv e-prints, arXiv: 2205.10449, 2022 | | 2022 |
George D. MagoulasProfessor, Director of the Birkbeck Knowledge Lab, Birkbeck College University of LondonVerified email at bbk.ac.uk
