In this paper, we propose a model of neural-network array composed of a number of MLPs (members), in which each member can be automatically trained to recognize the different dynamics of time series data. The proposed array adopts a position-based competitive learning methods that puts members with similar dynamics close to each other. The proposed array model intends to deal effectively with switching dynamics problems and produce a map of the dynamics.
|ホスト出版物のタイトル||Proceedings of the International Joint Conference on Neural Networks|
|出版ステータス||Published - 2001|
|イベント||International Joint Conference on Neural Networks (IJCNN'01) - Washington, DC|
継続期間: 2001 7月 15 → 2001 7月 19
|Other||International Joint Conference on Neural Networks (IJCNN'01)|
|Period||01/7/15 → 01/7/19|
ASJC Scopus subject areas