Search our Publications
Latest Publications
Claudius Gläser, Frank Joublin, Christian Goerick , "Homeostatic Development of Dynamic Neural Fields", Proceedings of the IEEE 7th International Conference on Development and Learning (ICDL), pp. 121-126, 2008.
AbstractDynamic neural field theory has become a popular technique for modeling the spatio-temporal evolution of activity within the cortex. When using neural fields the right balance between excitation and inhibition within the field is crucial for a stable operation. Finding this balance is a severe problem, particularly in face of experience-driven changes of synaptic strengths. Homeostatic plasticity where the objective function for each unit is to r...
Download Bibtex file Download PDF
Andreas Knoblauch , "Neural associative memory and the Willshaw-Palm probability distribution.", SIAM Journal on Applied Mathematics, vol. 69(1), pp. 169–196, 2008.
Download Bibtex file Download PDF
Jannik Fritsch, Thomas Michalke, Alexander Gepperth, Sven Bone, Falko Waibel, Marcus Kleinehagenbrock, Jens Gayko, Christian Goerick , "Towards a Human-like Vision System for Driver Assistance", Proceedings of the IEEE Intelligent Vehicles Symposium (IV), 2008.
AbstractSeveral Advanced Driver Assistance Systems realizing elementary perception and analysis tasks have been introduced to market in recent years. For example, collision mitigation brake systems detect the distance and relative velocity of vehicles in front to assess the risk of a rear-end collision in a clearly defined following situation. In order to go beyond such elementary analysis tasks, today's research is focusing more and more on powerful per...
Download Bibtex file Download PDF
Claudius Gläser, Frank Joublin, Christian Goerick , "Enhancing Topology Preservation during Neural Field Development via Wiring Length Minimization", Proceedings of the 18th International Conference on Artificial Neural Networks - ICANN 2008, Part I, Springer Verlag, pp. 593–602, 2008.
AbstractWe recently proposed a recurrent neural network model for the development of dynamic neural fields [1]. The learning regime incorporates homeostatic processes, such that the network is able to selforganize and maintain a stable operation mode even in face of experiencedriven changes in synaptic strengths. However, the learned mappings do not necessarily have to be topology preserving. Here we extend our model by incorporating another mechanism wh...
Download Bibtex file Download PDF
Yaochu Jin and Bernhard Sendhoff , "Pareto-based multi-objective machine learning: An overview and case studies", IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol. 38, no. 3, pp. 397-415, 2008.
Download Bibtex file Download PDF
Stephan Kirstein, Heiko Wersing, Horst-Michael Groß, Edgar Körner , "An Integrated System for Incremental Learning of Multiple Visual Categories", Proceedings of the International Conference on Neural Information Processing (ICONIP), 2008.
AbstractWe present a biologically inspired vision system able to incrementally learn multiple visual categories by interactively presenting several hand-held objects. The overall system is composed of a foregroundbackground separation part, several feature extraction methods and a life-long learning approach combining incremental learning with category specific feature selection. In contrast to most visual categorization approaches where typically each v...
Download Bibtex file Download PDF
Thomas Michalke, Robert Kastner, Jürgen Adamy, Sven Bone, Falko Waibel, Marcus Kleinehagenbrock, Jens Gayko, Alexander Gepperth, Jannik Fritsch, Christian Goerick , "An Attention-based System Approach for Scene Analysis in Driver Assistance", at - Automatisierungstechnik, vol. 56, no. 11, pp. 575-584, 2008.
Download Bibtex file Download PDF
Martin Brenn , "Dreidimensionale Topologieoptimierung mit Hilfe eines Zellwachstummodells", Darmstadt University of Technology, 2008.
Download Bibtex file Per Mail Request
Yaochu Jin and Bernhard Sendhoff , "Evolving in silico Bistable and Oscillatory Dynamics for Gene Regulatory Network Motifs", Congress on Evolutionary Computation, pp. pp.386-391, 2008.
Download Bibtex file Download PDF
Behzad Dariush, Michael Gienger, Arjun Arumbakkam, Christian Goerick, Youding Zhu, Kikuo Fujimura , "Online and markerless motion retargetting with kinematic constraints", IEEE International Conference on Intelligent Robot and Systems, 2008.
AbstractTransferring motion from a human demonstrator to a humanoid robot is an important step toward developing robots that are easily programmable and that can replicate or learn from observed human motion. The so called motion retargeting problem has been well studied and several offline solutions exist based on optimization approaches that rely on pre-recorded human motion data collected from a marker-based motion capture system. From the perspective...
Download Bibtex file Download PDF
1 ... 135 136 137 138 139 140 ... 170
Follow us
