DSpace Repository


Show simple item record

dc.contributor.author Baymukhamedov, М.F.
dc.contributor.author Yesslyamov ., S.G
dc.contributor.author Dr. Mustafa, Kemal Akgul
dc.date.accessioned 2019-05-27T06:30:41Z
dc.date.available 2019-05-27T06:30:41Z
dc.date.issued 2018
dc.identifier.uri http://repo.kspi.kz/handle/item/2941
dc.description.abstract here are technologies that allow combining several neural modules into a single neural network. The cascading procedure is designed to interface neural networks on data flow and error back propagation. This allows the use of the generic method for forward propagation modular networks training with arbitrary structure. The mathematical model of cascading neural networks is given. In case of cascade connection modules, the neural network learning can be made with different speeds of training for the incoming modules. Next, the article presents the tasks based on neural networks. Features that the task should have in order to justify the application of neural networks, and the neural network could solve it, are: - there are no algorithm or known principles for tasks solution, but there is a sufficient number of examples; - the task is characterized by large volumes of input data; - the data is either incomplete or redundant, noisy, partially contradictory. Neural networks are well suited for image recognition and solving prob-lems of classification, optimization and forecasting. ru_RU
dc.language.iso other ru_RU
dc.publisher PUBLISHINGS of Kostanay State Pedagogical University ru_RU
dc.subject neural network ru_RU
dc.subject cascading ru_RU
dc.subject model ru_RU
dc.subject training ru_RU
dc.subject tasks ru_RU
dc.subject modules ru_RU
dc.type Article ru_RU

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


My Account