Online Figure-Ground Segmentation with Adaptive Metrics in Generalized LVQ (2009)
Er Denecke, Heiko Wersing, Jochen J. Steil, Edgar Körner
We address the problem of fast figure-ground segmentation of single objects from cluttered backgrounds to improve object learning and recognition. For the segmentation, we use an initial foreground...
Robust object segmentation by adaptive metrics in Generalized LVQ (2009)
Er Denecke, Heiko Wersing, Jochen J. Steil, Edgar Körner
Abstract. We investigate the effect of several adaptive metrics in the context of figure-ground segregation, using Generalized LVQ to train a classifier for image regions. Extending the Euclidean...
Input Space Bifurcation Manifolds of RNNs (2009)
Robert Haschke, Jochen J. Steil
Abstract. We derive analytical expressions of local codim-1-bifurcations for a fully connected, additive, discrete-time RNN, where we regard the external inputs as bifurcation parameters. The...
Abstract Input Space Bifurcation Manifolds of Recurrent Neural Networks (2008)
Robert Haschke, Jochen J. Steil
We derive analytical expressions of local codimension-1 bifurcations for a fully connected, additive, discrete-time recurrent neural network (RNN), where we regard the external inputs as bifurcation...
Tutorial: Perspectives on Learning with RNNs (2008)
Abstract. We present an overview of current lines of research on learning with recurrent neural networks (RNNs). Topics covered are: understanding and unification of algorithms, theoretical...
Neural Dynamics for Task-Oriented Grouping of Communicating Agents (2008)
Abstract. Many real world problems are given in the form of multiple measurements comprising local descriptions or tasks. We propose that a dynamical organization of a population of communicating...
Frank Röthling, Robert Haschke, Jochen J. Steil, Helge Ritter
Abstract — We present a strategy for grasping of real world objects with two anthropomorphic hands, the three-fingered 9-DOF hydraulic TUM and the very dextrous 20-DOF pneumatic Bielefeld Shadow...
Sebastian Weng, Heiko Wersing, Jochen J. Steil, Helge Ritter
Abstract — We present a hybrid learning method bridging the fields of recurrent neural networks, unsupervised Hebbian learning, vector quantization, and supervised learning to implement a...
Unsupervised Clustering of Continuous (2008)
Trajectories Of Kinematic, Jochen J. Steil, Risto Koiva, Alessandro Sperduti
We explore the capability of the Self Organizing Map for structured data (SOM-SD) to compress continuous time data recorded from a kinematic tree, which can represent a robot or an artifical...
Igor B. Junger, Jochen J. Steil
A new type of sliding mode based on the denition of an input-dependent sliding surface and a corresponding discontinuous control algorithm is presented. The respective motion is called static sliding...
Tutorial: Perspectives on Learning with RNNs (2007)
Abstract. We present an overview of current lines of research on learning with recurrent neural networks (RNNs). Topics covered are: understanding and unification of algorithms, theoretical...
Input-Output Stability of Recurrent Neural Networks (2007)
Recurrent neural networks are an attractive tool for both practical applications and for the modeling of biological nerve nets, but their successful application requires an understanding of their...
Indices to Evaluate Self-Organizing Maps for Structures (2007)
Steil, Jochen J., Sperduti, Alessandro
Self-Organizing Maps for Structures (SOM-SD) are neural networks models capable of processing structured data, such as sequences and trees. The evaluation of the encoding quality achieved by these...
Recent trends in online learning for cognitive robotics (2006)
Jochen J. Steil, Heiko Wersing
Abstract. We present a review of recent trends in cognitive robotics that deal with online learning approaches to the acquisition of knowledge, control strategies and behaviors of a cognitive robot...
Recent trends in online learning for cognitive robotics (2006)
Abstract. We present a review of recent trends in cognitive robotics that deal with online learning approaches to the acquisition of knowledge, control strategies and behaviors of a cognitive robot...
Stability of backpropagation-decorrelation efficient O(N) recurrent learning (2005)
Abstract. We provide a stability analysis based on nonlinear feedback theory for the recently introduced backpropagation-decorrelation (BPDC) recurrent learning algorithm. For one output neuron BPDC...
A competitive layer model for feature binding and sensory segmentation (2001)
Heiko Wersing, Jochen J. Steil, Helge Ritter
We present a recurrent neural network for feature binding and sensory segmentation, the competitive layer model (CLM). The CLM uses topographically structured competitive and cooperative interactions...
A competitive layer model for feature binding and sensory segmentation (2001)
Heiko Wersing, Jochen J. Steil, Helge Ritter
We present a recurrent neural network for feature binding and sensory segmentation, the competitive layer model (CLM). The CLM uses topographically structured competitive and cooperative interactions...
A Competitive Layer Model for Feature Binding and Sensory Segmentation (2000)
Heiko Wersing, Jochen J. Steil, Helge Ritter
We present a recurrent neural network for feature binding and sensory segmentation, the competitive layer model (CLM). The CLM uses topographically structured competitive and cooperative interactions...
Input-Output Stability of Recurrent Neural Networks with Time-Varying Parameters (2000)
We provide input-output stability conditions for additive recurrent neural networks regarding them as dynamical operators between their input and output function spaces. The stability analysis is...
Input output stability of recurrent neural networks / (1999)
Zugl.: Bielefeld, University, Diss., 1999.
{j steil,helge} @ techfak.uni-bielefeld.de We analyse the stability of the input-output be-haviour of a recurrent network. It is trained to implement an operator implicitly given by the chaotic...
Maximisation of Stability Ranges for Recurrent Neural Networks Subject to on-Line Adaptation (1999)
. We present conditions for absolute stability of recurrent neural networks with time-varying weights based on the Popov theorem from non-linear feedback system theory. We show how to maximise the...
Maximisation of stability ranges for recurrent neural networks subject to on-line adaptation (1999)
Abstract. We present conditions for absolute stability of recurrent neural networks with time-varying weights based on the Popov theorem from non-linear feedback system theory. We show how to...
A layered recurrent neural network for feature grouping (1997)
Heiko Wersing, Jochen J. Steil, Helge Ritter
Abstract. We describe a recurrent network, the Competitive Layer Model (CLM) for feature grouping. The model uses a combination of cooperative and competitive interactions to partition a set of input...