On the Role of Topology for Neural Network Interpretation.
Jürgen Rahmel · 1996
. We investigate the information that is contained in the structure of a topology preserving neural network. In general considerations, we propose certain properties of the structure and formulate the respective expectable results of network interpretation. From the results we conclude that topology preservation as well as neuron distribution are highly influential for the network semantics and we propose a new network model that fits both needs. This so called SplitNet model dynamically constructs a hierarchically structured network that provides interpretability by neuron distribution, network topology and hierarchy of the network layers. 1 INTRODUCTION Topology preserving networks like the Self-Organizing Map (SOM) [3] are used for dimension reduction and visualization of data from various fields of applications. Tasks to be solved are generalization from training data and classification of previously unseen data records on the basis of the trained network. Classification is based ...