Theano: A Python framework for fast computation of mathematical expressions R Al-Rfou, G Alain, A Almahairi, C Angermueller, D Bahdanau, N Ballas, ... arXiv e-prints, arXiv: 1605.02688, 2016 | 1136* | 2016 |
On fast dropout and its applicability to recurrent networks J Bayer, C Osendorfer, D Korhammer, N Chen, S Urban, P van der Smagt arXiv preprint arXiv:1311.0701, 2013 | 94 | 2013 |
Optical pufs reloaded U Rührmair, C Hilgers, S Urban, A Weiershäuser, E Dinter, B Forster, ... Cryptology ePrint Archive, 2013 | 91 | 2013 |
Efficient movement representation by embedding dynamic movement primitives in deep autoencoders N Chen, J Bayer, S Urban, P Van Der Smagt 2015 IEEE-RAS 15th international conference on humanoid robots (Humanoids …, 2015 | 59 | 2015 |
Convolutional neural networks learn compact local image descriptors C Osendorfer, J Bayer, S Urban, P van der Smagt Neural Information Processing: 20th International Conference, ICONIP 2013 …, 2013 | 31 | 2013 |
Sensor calibration and hysteresis compensation with heteroscedastic gaussian processes S Urban, M Ludersdorfer, P Van Der Smagt IEEE Sensors Journal 15 (11), 6498-6506, 2015 | 28 | 2015 |
Computing grip force and torque from finger nail images using gaussian processes S Urban, J Bayer, C Osendorfer, G Westling, BB Edin, P Van Der Smagt 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2013 | 20 | 2013 |
Estimating finger grip force from an image of the hand using convolutional neural networks and gaussian processes N Chen, S Urban, C Osendorfer, J Bayer, P Van Der Smagt 2014 IEEE International Conference on Robotics and Automation (ICRA), 3137-3142, 2014 | 19 | 2014 |
Snookie: An autonomous underwater vehicle with artificial lateral-line system AN Vollmayr, S Sosnowski, S Urban, S Hirche, JL van Hemmen Flow Sensing in Air and Water: Behavioral, Neural and Engineering Principles …, 2014 | 15 | 2014 |
Neural Network Architectures and Activation Functions: A Gaussian Process Approach S Urban Technical University Munich, 2018 | 13 | 2018 |
A neural transfer function for a smooth and differentiable transition between additive and multiplicative interactions S Urban, P van der Smagt arXiv preprint arXiv:1503.05724, 2015 | 11 | 2015 |
Supervised spike-timing-dependent plasticity: A spatiotemporal neuronal learning rule for function approximation and decisions JMP Franosch, S Urban, JL van Hemmen Neural computation 25 (12), 3113-3130, 2013 | 11 | 2013 |
Revisiting Optical Physical Unclonable Functions. U Rührmair, C Hilgers, S Urban, A Weiershäuser, E Dinter, B Forster, ... IACR Cryptol. ePrint Arch. 2013, 215, 2013 | 11 | 2013 |
Training neural networks with implicit variance J Bayer, C Osendorfer, S Urban, P van der Smagt Neural Information Processing: 20th International Conference, ICONIP 2013 …, 2013 | 10 | 2013 |
Measuring fingertip forces from camera images for random finger poses N Chen, S Urban, J Bayer, P van der Smagt 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2015 | 9 | 2015 |
Unsupervised feature learning for low-level local image descriptors C Osendorfer, J Bayer, S Urban, P van der Smagt arXiv preprint arXiv:1301.2840, 2013 | 7 | 2013 |
Gaussian process neurons learn stochastic activation functions S Urban, M Basalla, P van der Smagt arXiv preprint arXiv:1711.11059, 2017 | 6 | 2017 |
climin-A pythonic framework for gradient-based function optimization J Bayer, C Osendorfer, S Diot-Girard, T Rueckstiess, S Urban TUM, Tech. Rep., 2015 | 6 | 2015 |
Automatic differentiation for tensor algebras S Urban, P van der Smagt arXiv preprint arXiv:1711.01348, 2017 | 2 | 2017 |
A Differentiable Transition Between Additive and Multiplicative Neurons W Köpp, P van der Smagt, S Urban arXiv preprint arXiv:1604.03736, 2016 | 2 | 2016 |