Extreme learning machine is a new scheme for learning the feedforward neural network, where the input weights and biases determining the nonlinear feature mapping are initiated randomly and are not learned. In this work we analyse approximation ability of the extreme learning machine depending on the activation function type and ranges from which input weights and biases are randomly generated....

This paper presents a parameterized Newton method using generalized Jacobians and a Broyden-like method for solving nonsmooth equations. The former ensures that the method is well-deened even when the generalized Jacobian is singular. The latter is constructed by using an approximation function which can be formed for nonsmooth equations arising from partial diierential equations and nonlinear ...

An application of Beta wavelet networks to synthesize pass-high and pass-low wavelet filters is investigated in this work. A Beta wavelet network is constructed using a parametric function called Beta function in order to resolve some nonlinear approximation problem. We combine the filter design theory with wavelet network approximation to synthesize perfect filter reconstruction. The order fil...

In this paper, we propose a class of penalty methods with stochastic approximation for solving stochastic nonlinear programming problems. We assume that only noisy gradients or function values of the objective function are available via calls to a stochastic first-order or zeroth-order oracle. In each iteration of the proposed methods, we minimize an exact penalty function which is nonsmooth an...

A neural network embedding learning control scheme is proposed in this paper, which addresses the performance optimization problem of a class nonlinear system with unknown dynamics and disturbance by combining novel function approximator an improved observer (DOB). We investigated mixture basic (MBF) to approximate system, allows approximation global scope, replacing traditional radial basis (R...

Studies convergence properties of radial basis function (RBF) networks for a large class of basis functions, and reviews the methods and results related to this topic. The authors obtain the network parameters through empirical risk minimization. The authors show the optimal nets to be consistent in the problem of nonlinear function approximation and in nonparametric classification. For the cla...

This paper focuses on the update step of Bayesian nonlinear ltering. We rst derive the unscented Gaussian likelihood approximation lter (UGLAF), which provides a Gaussian approximation to the likelihood by applying the unscented transformation to the inverse of the measurement function. The UGLAF approximation is accurate in the cases where the unscented Kalman lter (UKF) is not and the other w...

Voice activity detection (VAD) is used to detect whether the acoustic signal belongs to speech or non-speech clusters based on the statistical distribution of the acoustic features. Traditional VAD algorithms are applied in a linear transformed space without any constraint relating to the special characteristics speech or noise. As a result, the VAD algorithms are not robust to noise interferen...

-This paper focuses the function approximation capability of feed forward neural network (FFNN). A Graphical user Interface (GUI) system has been developed and tested for function approximation. This GUI system can approximate any nonlinear/linear function which can have any number of input variable and six output variables. Configuration of neural network can be set from a single GUI window. A...