H
Helge Ritter
Researcher at Bielefeld University
Publications - 596
Citations - 14078
Helge Ritter is an academic researcher from Bielefeld University. The author has contributed to research in topics: Artificial neural network & Robot. The author has an hindex of 57, co-authored 585 publications receiving 13213 citations. Previous affiliations of Helge Ritter include Heidelberg University & Citec.
Papers
More filters
Journal ArticleDOI
Self-organizing semantic maps
Helge Ritter,Teuvo Kohonen +1 more
TL;DR: Self-organized formation of topographic maps for abstract data, such as words, is demonstrated and it is argued that a similar process may be at work in the brain.
Journal ArticleDOI
BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm
TL;DR: An approach to analyze data from the P300 speller paradigm using the machine-learning technique support vector machines, which is fast, requires only 10 electrode positions and demands only a small amount of preprocessing.
Book
Neural computation and self-organizing maps : an introduction
TL;DR: In this article, a comprehensive introduction to neural networks and neural information processing is presented. And the most important models of neural networks are described and how they contribute to our understanding of information and organization processes in the brain.
Journal ArticleDOI
Topology-conserving maps for learning visuo-motor-coordination
TL;DR: It is shown that both arm kinematics and arm dynamics can be learned, if a suitable representation for the map output is used, due to the topology-conserving property of the map spatially neighboring neurons can learn cooperatively.
Journal ArticleDOI
Convergence properties of Kohonen's topology conserving maps: fluctuations, stability, and dimension selection
Helge Ritter,Klaus Schulten +1 more
TL;DR: In this article, a Markovian algorithm for the formation of topologically correct feature maps was proposed, where the maps from a space of input signals onto an array of formal neurons are generated by a learning scheme driven by a random sequence of input samples.