Udo Seiffert

Learn More
This paper describes the employment of an 'Adaptive Growing Three-Dimensional Self-Organizing Map' for the classification of images. 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 growing feature is presented. By means of some selected(More)
Multiple Layer Perceptron networks trained with backpropagation algorithm are very frequently used to solve a wide variety of real-world problems. Usually a gradient descent algorithm is used to adapt the weights based on a comparison between the desired and actual network response to a given input stimulus. All training pairs, each consisting of input(More)
Seeds are complex structures composed of several maternal and filial tissues which undergo rapid changes during development. In this review, the barley grain is taken as a cereal seed model. Following a brief description of the developing grain, recent progress in grain development modeling is described. 3-D/4-D models based on histological sections or(More)
A correlation-based similarity measure is derived for generalized relevance learning vector quantization (GRLVQ). The resulting GRLVQ-C classifier makes Pearson correlation available in a classification cost framework where data prototypes and global attribute weighting terms are adapted into directions of minimum cost function values. In contrast to the(More)
The barley pathogen Rhynchosporium commune secretes necrosis-inducing proteins NIP1, NIP2, and NIP3. Expression analysis revealed that NIP1 transcripts appear to be present in fungal spores already, whereas NIP2 and NIP3 are synthesized after inoculation of host plants. To assess the contribution of the three effector proteins to disease development,(More)
The development of fungal pathogens can be quantified easily at the level of spore germination or penetration. However, the exact quantification of hyphal growth rates after initial, successful host invasion is much more difficult. Here, we report on the development of a new pattern recognition software (HyphArea) for automated quantitative analysis of(More)
Multidimensional Scaling (MDS) is a powerful dimension reduction technique for embedding high-dimensional data into a lowdimensional target space. Thereby, the distance relationships in the source are reconstructed in the target space as best as possible according to a given embedding criterion. Here, a new stress function with intuitive properties and a(More)