A Nonlinear Neural FIR Filter With An Adaptive Activation Function
نویسندگان
چکیده
An adaptive amplitude normalized nonlinear gradient descent (AANNGD) algorithm for the class of nonlinear finite impulse response (FIR) adaptive filters (dynamical perceptron) 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 rigour, 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.
منابع مشابه
Nonlinear adaptive filtering with FIR synapses and adaptive activation functions
This paper focuses on multilayer perceptron neural networks where the activation functions are adaptive and where each neuron synapse is modelled by a finite impulse response (FIR) filter. A simplified architecture consisting of a variable activation (VA) function which is sandwiched between two FIR synapses is studied. The VA function consists of a mixed linear-tanh sigmoid with a parameter wh...
متن کاملA complex-valued nonlinear neural adaptive filter with a gradient adaptive amplitude of the activation function
A complex-valued nonlinear gradient descent (CNGD) learning algorithm for a simple finite impulse response (FIR) nonlinear neural adaptive filter with an adaptive amplitude of the complex activation function is proposed. This way the amplitude of the complex-valued analytic nonlinear activation function of a neuron in the learning algorithm is made gradient adaptive to give the complex-valued a...
متن کاملComplex-valued neural networks with adaptive spline activation function for digital-radio-links nonlinear equalization
In this paper, a new complex-valued neural network based on adaptive activation functions is proposed. By varying the control points of a pair of Catmull–Rom cubic splines, which are used as an adaptable activation function, this new kind of neural network can be implemented as a very simple structure that is able to improve the generalization capabilities using few training samples. Due to its...
متن کاملTarget Detection in Bistatic Passive Radars by Using Adaptive Processing Based on Correntropy Cost Function
In this paper a novel method is introduced for target detection in bistatic passive radars which uses the concept of correntropy to distinguish correct targets from false detections. In proposed method the history of each cell of ambiguity function is modeled as a stochastic process. Then the stochastic processes consist the noise are differentiated from those consisting targets by constructing...
متن کاملAdaptive Channel Equalizer using Combination of FIR and Functional Link Artificial Neural Network for Complex Signals
− This paper proposes an adaptive nonlinear channel equalizer by using combination of finite impulse response (FIR) filter and functional link artificial neural (FLANN) network (CFFLANN) capable of equalizing complex multilevel signals. The equalizer is designed to remove linear and nonlinear distortion produced by nonlinear channel. FLANN section removes the nonlinear distortions and FIR secti...
متن کامل