Buscar
Mostrando ítems 1-10 de 2122
A radial basis function network (RBFN) for function approximation
(IEEE, 1999-01-01)
A radial basis function network (RBFN) circuit for function approximation is presented. Simulation and experimental results show that the network has good approximation capabilities. The RBFN was a squared hyperbolic secant ...
Approximation of hyperbolic tangent activation function using hybrid methods
(2013-09-16)
Artificial Neural Networks are widely used in various applications in engineering, as such solutions of nonlinear problems. The implementation of this technique in reconfigurable devices is a great challenge to researchers ...
Radial basis function network applied to the linearization of a voltage controlled oscillator
(2007-12-01)
An analog circuit that implements a radial basis function network is presented. The proposed circuit allows the adjustment of all shape parameters of the radial functions, i.e., amplitude, center and width. The implemented ...
Comparative study between powers of sigmoid functions, MLP-backpropagation and polynomials in function approximation problems
(Spie - Int Soc Optical Engineering, 1999-01-01)
Function approximation is a very important task in environments where the computation has to be based on extracting information from data samples in real world processes. So, the development of new mathematical model is a ...
Chaos induced by turbulent and erratic functions
(2009-12-01)
Let (X, d) be a compact metric space and f: X → X a continuous function and consider the hyperspace (K(X), H) of all nonempty compact subsets of X endowed with the Hausdorff metric induced by d. Let f̄: K(X) → K (X) be ...
Activation function study for wavelet network
(1997-12-01)
The main purpose of this paper is to investigate theoretically and experimentally the use of family of Polynomial Powers of the Sigmoid (PPS) Function Networks applied in speech signal representation and function approximation. ...
Chaos induced by turbulent and erratic functions
(European Soc Fuzzy Logic & Technology, 2009-01-01)
Let ( X, d) be a compact metric space and f : X -> X a continuous function and consider the hyperspace (K(X), H) of all nonempty compact subsets of X endowed with the Hausdorff metric induced by d. Let (f) over bar : K(X) ...
Multidimensional polynomial powers of sigmoid (PPS) Wavelet neural networks
(Insticc-inst Syst Technologies Information Control & Communication, 2008-01-01)
Wavelet functions have been used as the activation function in feedforward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural ...
Multidimensional Polynomial Powers of Sigmoid (PPS) wavelet neural networks
(2008-11-13)
Wavelet functions have been used as the activation function in feedforward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural ...
Some properties of the Riemannian distance function and the position vector X, with applications to the construction of Lyapunov functions
(Ieee, 2010-01-01)
The quadratic distance function on a Riemannian manifold can be expressed in terms of the position vector, which in turn can be constructed using geodesic normal coordinates through consideration of the exponential map. ...