393 research outputs found
OOP: Object-Oriented-Priority for Motion Saliency Maps
No full textBelardinelli A, Schneider WX, Steil JJ. OOP: Object-Oriented-Priority for Motion Saliency Maps. In: Workshop on Brain Inspired Cognitive Systems. 2010: 370-381
Platform Portable Anthropomorphic Grasping with the Bielefeld 20-DOF Shadow and 9-DOF TUM Hand
No full textRöthling F, Haschke R, Steil JJ, Ritter H. Platform Portable Anthropomorphic Grasping with the Bielefeld 20-DOF Shadow and 9-DOF TUM Hand. In: Proc. Int. Conf. on Intelligent Robots and Systems (IROS). IEEE; 2007: 2951-2956
Roboterlernen ohne Grenzen? Lernende Roboter und ethische Fragen
No full textSteil JJ. Roboterlernen ohne Grenzen? Lernende Roboter und ethische Fragen. In: Sammelband zur Konferenz Roboterethik. In Press
Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning
No full textSteil JJ. Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning. Neural Networks. 2007;20(3):353-364
Robust control in closed loops realised by fast signal transmission of infinite gain neurons
No full textSteil JJ. Robust control in closed loops realised by fast signal transmission of infinite gain neurons. In: Proc. Int. Conf. Artificial Neural Networks. Vol 1. 2000: 260-266
Regularization by Intrinsic Plasticity and its Synergies with Recurrence for Random Projection Methods
No full textNeumann K, Emmerich C, Steil JJ. Regularization by Intrinsic Plasticity and its Synergies with Recurrence for Random Projection Methods. Journal of Intelligent Learning Systems and Applications. 2012;4(3):230-246.Neural networks based on high-dimensional random feature generation have become popular under the notions extreme learning machine (ELM) and reservoir computing (RC). We provide an in-depth analysis of such networks with respect to feature selection, model complexity, and regularization. Starting from an ELM, we show how recurrent connections increase the effective complexity leading to reservoir networks. On the contrary, intrinsic plasticity (IP), a biologically inspired, unsupervised learning rule, acts as a task-specific feature regularizer, which tunes the effective model complexity. Combing both mechanisms in the framework of static reservoir computing, we achieve an excellent balance of feature complexity and regularization, which provides an impressive robustness to other model selection parameters like network size, initialization ranges, or the regularization parameter of the output learning. We demonstrate the advantages on several synthetic data as well as on benchmark tasks from the UCI repository providing practical insights how to use high-dimensional random networks for data processin
Editorial Special Corner on Cognitive Robotics
No full textKopp S, Steil J. Editorial Special Corner on Cognitive Robotics. Cognitive Processing. 2011;12(4):317-318
Neural competition for motion segmentation
No full textSteffen JF, Pardowitz M, Steil JJ, Ritter H. Neural competition for motion segmentation. In: 18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). Bruges (Belgium): d-side; 2010: 59-64
Dynamically-consistent Generalized Hierarchical Control
No full textDehio N, Steil JJ. Dynamically-consistent Generalized Hierarchical Control. In: IEEE/RSJ Int. Conf. on Robotics and Automation. 2019
Input-Output Stability of Recurrent Neural Networks
No full textSteil JJ. Input-Output Stability of Recurrent Neural Networks. Göttingen: Cuvillier; 1999
- …
