| Training and analysing deep recurrent neural networks M Hermans, B Schrauwen Advances in neural information processing systems 26, 2013 | 747 | 2013 |
| A differentiable physics engine for deep learning in robotics J Degrave, M Hermans, J Dambre, F Wyffels Frontiers in neurorobotics 13, 6, 2019 | 254 | 2019 |
| Recurrent kernel machines: Computing with infinite echo state networks M Hermans, B Schrauwen Neural Computation 24 (1), 104-133, 2012 | 114 | 2012 |
| Memory in linear recurrent neural networks in continuous time M Hermans, B Schrauwen Neural Networks 23 (3), 341-355, 2010 | 96 | 2010 |
| Online training of an opto-electronic reservoir computer applied to real-time channel equalization P Antonik, F Duport, M Hermans, A Smerieri, M Haelterman, S Massar IEEE Transactions on Neural Networks and Learning Systems 28 (11), 2686-2698, 2016 | 90 | 2016 |
| Trainable hardware for dynamical computing using error backpropagation through physical media M Hermans, M Burm, T Van Vaerenbergh, J Dambre, P Bienstman Nature communications 6 (1), 6729, 2015 | 79 | 2015 |
| Photonic Delay Systems as Machine Learning Implementations M Hermans, M Soriano, J Dambre, P Bienstman, I Fischer JMLR 16, 2081-2097, 2015 | 57 | 2015 |
| Memristor models for machine learning JP Carbajal, J Dambre, M Hermans, B Schrauwen Neural computation 27 (3), 725-747, 2015 | 48 | 2015 |
| Automated design of complex dynamic systems M Hermans, B Schrauwen, P Bienstman, J Dambre PloS one 9 (1), e86696, 2014 | 43 | 2014 |
| Embodiment of learning in electro-optical signal processors M Hermans, P Antonik, M Haelterman, S Massar Physical review letters 117 (12), 128301, 2016 | 40 | 2016 |
| Towards pattern generation and chaotic series prediction with photonic reservoir computers P Antonik, M Hermans, F Duport, M Haelterman, S Massar Real-time Measurements, Rogue Events, and Emerging Applications 9732, 21-32, 2016 | 33 | 2016 |
| Optoelectronic systems trained with backpropagation through time M Hermans, J Dambre, P Bienstman IEEE transactions on neural networks and learning systems 26 (7), 1545-1550, 2014 | 30 | 2014 |
| Memory in reservoirs for high dimensional input M Hermans, B Schrauwen The 2010 international joint conference on neural networks (IJCNN), 1-7, 2010 | 24 | 2010 |
| Building robots as a tool to motivate students into an engineering education M Hermans, B Schrauwen 1st International conference on Robotics in Education (RiE 2010), 49-52, 2010 | 17 | 2010 |
| MACOP modular architecture with control primitives T Waegeman, M Hermans, B Schrauwen Frontiers in computational neuroscience 7, 99, 2013 | 15 | 2013 |
| Online training of an opto-electronic reservoir computer P Antonik, F Duport, A Smerieri, M Hermans, M Haelterman, S Massar Neural Information Processing: 22nd International Conference, ICONIP 2015 …, 2015 | 14 | 2015 |
| One step backpropagation through time for learning input mapping in reservoir computing applied to speech recognition M Hermans, B Schrauwen Proceedings of 2010 IEEE International Symposium on Circuits and Systems …, 2010 | 14 | 2010 |
| Random pattern and frequency generation using a photonic reservoir computer with output feedback P Antonik, M Hermans, M Haelterman, S Massar Neural Processing Letters 47, 1041-1054, 2018 | 11 | 2018 |
| Photonic reservoir computer with output feedback for chaotic time series prediction P Antonik, M Hermans, M Haelterman, S Massar 2017 International Joint Conference on Neural Networks (IJCNN), 2407-2413, 2017 | 10 | 2017 |
| Toward unified hybrid simulation techniques for spiking neural networks M D'Haene, M Hermans, B Schrauwen Neural computation 26 (6), 1055-1079, 2014 | 9 | 2014 |
Benjamin SchrauwenProfessor of Machine Learning, Ghent UniversityVerified email at ugent.be
