Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Udo Seiffert is active.

Publication


Featured researches published by Udo Seiffert.


Archive | 2001

Multi-Dimensional Self-Organizing Maps on Massively Parallel Hardware

Udo Seiffert; Bernd Michaelis

Although available (sequential) computer hardware is very powerful nowadays, the implementation of artificial neural networks on massively parallel hardware is still undoubtedly of high interest, not only under an academic point of view. This paper presents an implementation of multi-dimensional Self-Organizing Maps on a scalable SIMD structure of a CNAPS computer with up to 512 parallel processors.


Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584) | 2001

Directed random search for multiple layer perceptron training

Udo Seiffert; Bernd Michaelis

Although backpropagation (BP) is commonly used to train multiple layer perceptron (MLP) neural networks and its original algorithm has been significantly improved several times, it still suffers from some drawbacks like being slow, getting stuck in local minima or being bound to constraints regarding the activation (transfer) function of the neurons. The paper presents the substitution of backpropagation with a random search technique which has been enhanced by a directed component. By means of some benchmark problems, a case study shows general potential application fields as well as advantages and disadvantages of both the backpropagation and the directed random search (DRS).


Information Sciences | 1997

Estimating motion parameters with three-dimensional self-organizing maps

Udo Seiffert; Bernd Michaelis

Abstract The importance of analyzing moving scenes within the wide area of digital image processing is increasingly high. Although a simple detection of object velocity by neural networks has been considered in previously published papers, an implementation of artificial neural networks using a priori information for motion analysis is still quite rare. This paper shows the benefits from artificial neural networks, and from using a priori information about the contents of the history in the image sequence to improve the accuracy and speed of estimating motion parameters in the cases of distorted or overlapped objects. In the first place, it introduces three-dimensional Self-Organizing Maps (SOM) with two-dimensional input layers.


new zealand international two stream conference on artificial neural networks and expert systems | 1995

Three-dimensional self-organizing maps for classification of image properties

Udo Seiffert; Bernd Michaelis

The importance of analysing moving scenes within the wide area of digital image processing is increasingly high. Although a simple detection of object velocity by biological models has been considered in previously published papers (A. Tsukamoto et al., 1993; S. Wimbauer et al., 1994; J. Hogden et al., 1993), an implementation of artificial neural networks using a priori information for motion analysis is still quite rare. The paper shows the benefits from artificial neural networks and from using a priori information about the contents of the history in the image sequence to improve accuracy and speed of estimating motion parameters in the cases of distorted or overlapped objects. Firstly, it introduces 3 dimensional self organizing maps (SOM) with 2 dimensional input layers.


Lecture Notes in Computer Science | 2004

Improving Image Processing Systems by Artificial Neural Networks

R. Rebmann; Bernd Michaelis; Gerald Krell; Udo Seiffert; F. Püschel

Document analysis systems require documents in electronic format. An image acquisition and display system for scanning and saving documents is presented, whereby the recognition capability (for example, series-connected OCR systems) is improved by correction components. Components for improving image acquisition, archiving documents and for reducing compression errors during archiving are integrated in the overall solution. The deployed components are suitably trained artificial neural networks. The projected improvements are assessed.


intelligent information systems | 1996

Adaptive three-dimensional self-organizing map with a two-dimensional input layer

Udo Seiffert; Bernd Michaelis

This paper introduces an adaptive growing three-dimensional self-organizing map with the special feature of a matrix input layer instead of a one-dimensional vector. First a short description of growing SOMs is given and the fundamental advantages are mentioned. Then an extension of the original SOM from two to three dimensions with a growing feature is presented. By means of a selected example the general behaviour of the algorithm is illustrated.


Archive | 1998

Classification of 3-D Dendritic Spines using Self-Organizing Maps

Gerd Sommerkorn; Udo Seiffert; D. Surmeli; Andreas Herzog; Bernd Michaelis; K. Braun

This work in progress shows a method for classifying dendritic spines by their shape. Focal points are the extraction of features from three-dimensional spine data and the following classification of the spines. Hence there will be only little reflection of biological aspects of this problem. Feature extraction based on moments and spherical coordinates will be discussed. Furthermore, this paper shows and describes a modified kind of self organizing maps (SOM)), which is used for the classification of the dendritic spines.


International Journal of Neural Systems | 1997

Growing 3D-SOMs with 2D-Input Layer as a Classification Tool in a Motion Detection System

Udo Seiffert; Bernd Michaelis


Archive | 1997

CLASSIFICATION OF 3D DENDRITIC SPINES USING SOM

Gerd Sommerkorn; Udo Seiffert; Dimitrij Surmeli; Bernd Michaelis; Katharina Braun


Archive | 2000

ON THE GRADIENT DESCENT IN BACKPROPAGATION AND ITS SUBSTITUTION BY A GENETIC ALGORITHM

Udo Seiffert; Bernd Michaelis

Collaboration


Dive into the Udo Seiffert's collaboration.

Top Co-Authors

Avatar

Bernd Michaelis

Otto-von-Guericke University Magdeburg

View shared research outputs
Top Co-Authors

Avatar

Gerd Sommerkorn

Otto-von-Guericke University Magdeburg

View shared research outputs
Top Co-Authors

Avatar

Andreas Herzog

Otto-von-Guericke University Magdeburg

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

D. Surmeli

Otto-von-Guericke University Magdeburg

View shared research outputs
Top Co-Authors

Avatar

Dimitrij Surmeli

Otto-von-Guericke University Magdeburg

View shared research outputs
Top Co-Authors

Avatar

F. Püschel

Otto-von-Guericke University Magdeburg

View shared research outputs
Top Co-Authors

Avatar

Gerald Krell

Otto-von-Guericke University Magdeburg

View shared research outputs
Top Co-Authors

Avatar

R. Rebmann

Otto-von-Guericke University Magdeburg

View shared research outputs
Top Co-Authors

Avatar

Werner Zuschratter

Max Delbrück Center for Molecular Medicine

View shared research outputs
Researchain Logo
Decentralizing Knowledge