A nonlinear neural fir filter with an adaptive activation function | Zendy

Su Lee | Zendy; Milorad Bozic | Zendy; Danilo Mandić | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

A nonlinear neural fir filter with an adaptive activation function

Author(s) -

Su Lee,

Milorad Bozic,

Danilo Mandić

Publication year - 2003

Publication title -

journal of automatic control

Language(s) - English

Resource type - Journals

eISSN - 2406-0984

pISSN - 1450-9903

DOI - 10.2298/jac0301001l

Subject(s) - nonlinear system , adaptive filter , finite impulse response , control theory (sociology) , computer science , gradient descent , activation function , amplitude , adaptive algorithm , artificial neural network , filter (signal processing) , algorithm , physics , artificial intelligence , control (management) , quantum mechanics , computer vision

An adaptive amplitude normalized nonlinear gradient descent (AANNGD) algorithm for the class of nonlinear finite impulse response (FIR) adaptive filters (dynamical perception) is introduced. This is achieved by making the amplitude of the nonlinear activation function gradient adaptive. The proposed learning algorithm is suitable for processing of nonlinear and nonstationary signals with a large dynamical range, and removes the unwanted effect of saturation nonlinearities. For rigor, sensitivity analysis is performed and the improved performance of the AANNGD algorithm over the standard LMS, NGD, NNGD, the fully adaptive NNGD (FANNGD) and the sign algorithm is verified by simulations on nonlinear and nonstationary inputs with large dynamics

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