Search academic texts

Information × Registration Number 0212U004062, 0110U000114 , R & D reports Title Research self-organizing treelike neural frames. popup.stage_title Head Kovalevskii Sergey V., Registration Date 24-01-2012 Organization Donbass State Engineering Academy popup.description2 Research object: treelike neural networks. Purpose: further development of theory of neural networks technologies in area of design of the difficult systems and objects. Theoretical and practical results: the method of transformation of co-ordinates is investigational in part of his application at tuning of cascade treelike neural networks; going is developed near the topology placing of neural elements in the output cards of treelike cascade neural networks for their practical application. Scientific novelty: the methods of synthesis and teaching of treelike cascade neural networks are developed; the method of normalization of basic data got further development for neural networks. Efficiency: the offered developments allow improving quality of design of objects and prognostication of their indexes. Application domain: objects, described as difficult systems. The method of normalization of basic data is developed for neural networks; the methods of forming of architecture of treelike cascade neural networks are probed; principles of synthesis of treelike cascade neural networks are developed; the method of transformation of co-ordinates is analyzed from point of his application for tuning of cascade neural networks. Product Description popup.authors Гітіс Веніамін Борисович Ковалевська Олена Сергіївна Ковалевський Сергій Вадимович popup.nrat_date 2020-04-02 Close