Dynamic topology representing networks

In the present paper, we propose a new algorithm, namely the Dynamic Topology Representing Networks (DTRN) for learning both topology and clustering information from input data. In contrast to other models with adaptive architecture of this kind, the DTRN algorithm adaptively grows the number of output nodes by applying a vigilance test. The clustering procedure is based on a winner-take-quota learning strategy in conjunction with an annealing process in order to minimize the associated mean square error. A competitive Hebbian rule is applied to learn the global topology information concurrently with the clustering process. The topology information learned is also utilized for dynamically deleting the nodes and for the annealing process. Properties of the DTRN algorithm will be discussed. Extensive simulations will be provided to characterize the effectiveness of the new algorithm in topology preserving, learning speed, and classification tasks as compared to other algorithms of the same nature.