19 Publikationen
-
-
2015 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2760762Lemme, A., & Steil, J.J., 2015. A flat neural network architecture to represent movement primitives with integrated sequencing. Presented at the European Symposium on Artificial Neural Networks, Brügge.PUB
-
2014 | Datenpublikation | PUB-ID: 2678439Lemme, A., et al., 2014. Multi-criteria benchmarking of movement generating dynamical systems for learning-from-demonstrations, Bielefeld University.PUB | Dateien verfügbar | DOI
-
2014 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2698361Lemme, A., Reinhart, F., & Steil, J.J., 2014. Semi-supervised Bootstrapping of a Movement Primitive Library from Complex Trajectories. Presented at the IEEE-RAS INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS, Madrid.PUB
-
-
-
-
-
-
2013 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2637629Soltoggio, A., et al., 2013. Learning the rules of a game: neural conditioning in human-robot interaction with delayed rewards. Presented at the Int. Conference on Developmental Learning and Epigenetic Robotics, Osaka, JP.PUB
-
-
-
-
2012 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2465822Freire, A., et al., 2012. Learning visuo-motor coordination for pointing without depth calculation. In Proc. European Symposium on Artificial Neural Networks. d-facto, pp. 91-96.PUB
-
2012 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2465826Nordmann, A., et al., 2012. Teaching Nullspace Constraints in Physical Human-Robot Interaction using Reservoir Computing. In Institute of Electrical and Electronics Engineers, ed. International Conference on Robotics and Automation. St. Paul: IEEE, pp. 1868-1875.PUB | DOI
-
-
-
2010 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2141984Lemme, A., Reinhart, F., & Steil, J.J., 2010. Efficient online learning of a non-negative sparse autoencoder. In European Symposium Artificial Neural Networks. Bruges: d-facto, pp. 1-6.PUB
-
2010 | Konferenzbeitrag | Veröffentlicht | PUB-ID: 2141992Wrede, S., et al., 2010. Interactive Learning of Inverse Kinematics with Nullspace Constraints using Recurrent Neural Networks. In Proc. 20. Workshop on Computational Intelligence. Dortmund: Fachausschuss Computational Intelligence der VDI/VDE-Gesellschaft Mess- und Automatisierungstechnik.PUB