Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
408825 | Neurocomputing | 2009 | 14 Pages |
The architecture and learning procedure of a novel artificial immune network, referred to as tree structured artificial immune network (TSAIN), are described in this paper. One major difference between this model and current models is that the topological structure can be strictly guaranteed as a tree, which allows to analyze the presented data (antigens) hierarchically. The other is that a novel antibody reaction mechanism inspired from the self-organizing map (SOM) is adopted in order to maintain consistency between the shape space metric and the topological metric, which is an important objective in high-dimensional data analysis. Moreover, several novel immune operators are also employed to improve the quality of the antibody population as well as to control its size. It is qualitatively demonstrated as well as quantitatively verified on a 3-D synthetic dataset and Iris dataset that TSAIN exhibits promising data visualization capability and low vector quantization error. We also use three well-known topology preservation measures to validate the topology preservation capability of our proposed model.