Stephan Rudolph, Steffen Brückner,
Intedependencies in Data-Preprocessing, Training Methods and Neural Network Topology Generation
in: Proc. of SPIE Vol 4739, Applications amd Science of Computational Intelligence V
Orlando, FL, USA, 1-4 April 2002

Abstract. Artificial neural networks are adaptive methods which can be trained to approximate a functional relationship implicitly encoded in training data. A large variety of neural network types (e.g. linear versus non-linear) gives rise to principal questions about the appropriateness of data pre-processing techniques, training methodologies, the resulting neural net-work topology and possible interdependencies thereof. The a posteriori interpretation of the numerical results gives hints for some guidelines for neural network applications in engineering applications. Data pre-processing techniques are a powerful means for pre-structuring the problem setting of function approximation through an adaptive training procedure. Especially integral transforms may change the nature of the training problem significantly without loss of generality if carefully selected and represent an excellent opportunity to incorporate additional knowledge about the process to improve the training and the result interpretation. Some numerical examples from engineering domains are used to illustrate the theoretical arguments in the context of a practical setting.

Keywords: Neural Networks, Data Pre-processing, Topology Generation, Integral Transforms

back

back