Architecture analysis of MLP by geometrical interpretation

Traditionally, the main focus regarding the architecture selection of a multilayer perceptron (MLP) has been centered upon the growing and pruning and the evolutionary algorithms, in which a priori information regarding the geometrical shape of the target function is usually not exploited. In contrast to this, we demonstrate that it is the geometrical information that can simplify the task of architecture selection significantly. We wish to suggest some general guidelines for selecting the architecture of the MLP, provided that the basic geometrical shape of the target function is known in advance, or can be perceived from the training data. These guidelines are based on the geometrical interpretation of the weights, the biases, and the number of hidden neurons and layers. The controversial issue of whether the four-layered MLP is superior to the three-layered MLP is also carefully examined with this geometrical interpretation.