Search our Publications
Latest Publications
Xavier Domont, Martin Ernst Heckmann, Heiko Wersing, Frank Joublin, Stefan Menzel, Bernhard Sendhoff, Christian Goerick , "Word Recognition with a Hierarchical Neural Network", Advances in Nonlinear Speech Processing, pp. 142-151, 2007.
AbstractIn this paper we propose a feedforward neural network for syllable recognition. The core of the recognition system is based on a hierarchical architecture initially developed for visual object recognition. We show that, given the similarities between the primary auditory and visual cortexes, such a system can successfully be used for speech recognition. Syllables are used as basic units for the recognition. Their spectrograms, computed using a Ga...
Download Bibtex file Download PDF
Nils Einecke, Julian Eggert, Sven Hellbach, Edgar Körner , "Walking the manifold without falling off", Proceedings of the 14th International Conference on Neual Information Processing (ICONIP), pp. 653-662, 2007.
AbstractHaving a good description of an object’s appearance is crucial for good object tracking. However, modeling the whole appearance of an object is difficult because of the high dimensional and nonlinear character of the appearance. To tackle the first problem we apply nonlinear dimensionality reduction approaches on multiple views of an object in order to extract the appearance manifold of the object and to embed it into a lower dimensional space. T...
Download Bibtex file Download PDF
Marc-Oliver Gewaltig , "Simulation Technologie for large neural systems.", Recent developments, chances and limitations of modern brain research., Technologie Ausschuss des Deutschen Bundestags, 2006.
AbstractIn computational neuroscience, simulations are an important tool to investigate and answer questions which are not tractable by experimental methods. They allow us to explicitly test models of information processing, by constructing models according to the hypothesized principles. Most computer models of neural systems focus on the properties of single neurons or small networks of neurons (see 2.2.2). However, in order to understand the fundament...
Download Bibtex file
Hans-Georg Beyer and Bernhard Sendhoff , "Functions with Noise-Induced Multi-Modality: A Test for Evolutionary Robust Optimization – Properties and Performance Analysis", IEEE Transactions on Evolutionary Computation, vol. 10, no. 5, pp. 507-526, 2006.
Download Bibtex file Download PDF
Jochen Steil and Heiko Wersing , "Recent trends in online learning for cognitive robotics", Proceedings of the European Symposium on Neural Networks, pp. 77-88, 2006.
Download Bibtex file Download PDF
Inna Mikhailova, Werner von Seelen, Christian Goerick , "Usage of General Developmental Principles for Adaptation of Reactive Behavior", Proceedings of the Sixth International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, pp. 63-70, 2006.
AbstractWe propose a design of a self-motivational system which would be suitable for both adaptation and development scenarios. The core features of our design are: the usage of general rewards and building up on a reactive system. As a test case for our design we use the human-robot interaction via shared attention. We show that with addition of a general-purpose self-motivational mechanism the system can aquire a behavior for distinguishing between ob...
Download Bibtex file Download PDF
Kwasi Foli, Tatsuya Okabe, Markus Olhofer, Yaochu Jin, Bernhard Sendhoff , "Optimization of micro heat exchanger: CFD, analytical approach and multi-objective evolutionary algorithms", International Journal of Heat and Mass Transfer, vol. 49, pp. 1090-1099, 2006.
Download Bibtex file Download PDF
Heiko Wersing, Stephan Kirstein, Michael Götting, Holger Brandl, Mark Dunn, Inna Mikhailova, Christian Goerick, Jochen Steil, Helge Ritter, Edgar Körner , "A biologically motivated system for unconstrained online learning of visual objects", Proc. ICANN, Athens, pp. 508 – 517, 2006.
Download Bibtex file Download PDF
Till Steiner, Markus Olhofer, Bernhard Sendhoff , "Towards shape and structure optimization with evolutionary development", Proceedings of the ALife X: The Tenth International Conference on the Simulation and Synthesis of Living Systems, pp. 70-76, 2006.
AbstractWe present an approach to model an artificial developmental system based on cells that interact through gene regulatory networks for shape or structure optimization.Cell differentiation is accomplished by positional information provided by transcription factors that diffuse inside a simulated environment. Different actions such as cell division, apoptosis and cell-cell communication are implemented. The system is applied to a simple target shape ...
Download Bibtex file Download PDF
Aimin Zhou, Yaochu Jin, Qingfu Zhang, Bernhard Sendhoff, Edward Tsang , "Prediction-based population re-initialization for evolutionary dynamic multi-objective optimization", The 4th Int. Conf. on Evolutionary Multi-Criterion Optimization, 2006.
Download Bibtex file Per Mail Request
1 ... 159 160 161 162 163 164 ... 183
Follow us
