The Construction and Approximation of the Neural Network with Two Weights | Zendy

Zhiyong Quan | Zendy; Zhengqiu Zhang | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

The Construction and Approximation of the Neural Network with Two Weights

Author(s) -

Zhiyong Quan,

Zhengqiu Zhang

Publication year - 2014

Publication title -

journal of applied mathematics

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.307

H-Index - 43

eISSN - 1687-0042

pISSN - 1110-757X

DOI - 10.1155/2014/892653

Subject(s) - artificial neural network , sigmoid function , partition of unity , chen , fourier series , mathematics , nonlinear system , partition (number theory) , series (stratigraphy) , computer science , mathematical analysis , artificial intelligence , combinatorics , paleontology , physics , quantum mechanics , finite element method , biology , thermodynamics

The technique of approximate partition of unity, the way of Fourier series, and inequality technique are used to construct a neural network with two weights and with sigmoidal functions. Furthermore by using inequality technique, we provethat the neural network with two weights can more precisely approximate any nonlinear continuous function than BP neural network constructed in (Chen et al., 2012)

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research