Relation between Topological Organization and Learning Ability of Neural Networks

摘要

The objective of this study is to investigate the correlation between the internal topological organization in a neural network and the learning ability of the neural network. This study is motivated by the interesting neurophysiological examination that shows the significance of topographic map formation of adult mammals' brains to their learning ability and plasticity. In this study we propose a model of a layered neural network with Self-Organizing Map in its hidden layer which is connected to a Perceptron as a learning part. We run several simulations to show the significance of the topological order in helping the learning and relearning process.