Axel Doering

Learn More
A method for the construction of optimal structures for feedforward neural networks is introduced. On the basis of a construction of a graph of network structures and an evaluation value which is assigned to each of them, an heuristic search algorithm can be installed on this graph. The application of the A*-algorithm ensures, in theory, both the optimality(More)
A recently published idea is to use the A*-Algorithm to optimize the topology of Neural Networks. In this paper, optimization techniques are investigated that combine the A*-Algorithm with diierent parallel training algorithms, namely the backpropagation algorithm and several hybrid algorithms. The hybrid algorithms combine the backpropagation's steepest(More)
Zusammenfassung. Wir präsentieren einen automatischen Algorithmus zur Registrierung und Überlagerung von Fundusbildern zu großflächigen Kompositionsaufnahmen. Das Verfahren kombiniert flächenbasierte und punktbasierte Ansätze. Als Ähnlichkeitsmaß dient jeweils der normierte Korrelationskoeffizient, der sich im Vergleich zur Transinformation als robuster(More)
Under idealized assumptions (injnitely large training sets, ideal training algorithms that avoid local minima and su@cient Neural Network (NN) structures) trained NNs realize Bayes-Optimal Classijiers (BOCs) with identical costs as long as the training set is representative. Training sets with relative class frequencies different from the a priori class(More)