Radial Basis Function (RBF) networks provide a powerful learning architecture for neural networks [6]. We have implemented a RBF network in analog VLSI using the concept of bump-resistors. A bump-resistor is a nonlinear resistor whose conductance is a Gaussian-like function of the difference of two other voltages. The width of the Gaussian basis functions may be continuously varied so that the ...

In this paper we use radial basis functions to solve multivariable integral equations. We use collocation method for implementation. Numerical experiments show the accuracy of the method.

In this paper, a new method is introduced to solve a two-dimensional Fredholm integral equation. The method is based on the approximation by Gaussian radial basis functions and triangular nodes and weights. Also, a new quadrature is introduced to approximate the two dimensional integrals which is called the triangular method. The results of the example illustrate the accuracy of the proposed me...

In the 1990’s exponential-type error bounds appeared in the theory of radial basis functions. For multiquadric interpolation it is O(λ 1 d ) as d → 0, where λ is a constant satisfying 0 < λ < 1. For Gaussian interpolation it is O(C d) c′ d as d → 0 where C ′ and c are constants. In both cases the parameter d, called fill distance, measures the spacing of the points where interpolation occurs. T...

This paper proposes a Radial Basis Function Neural Network (RBFNN) which reproduces different Radial Basis Functions (RBFs) by means of a real parameter q, named q-Gaussian RBFNN. The architecture, weights and node topology are learnt through a Hybrid Algorithm (HA) with the iRprop+ algorithm as the local improvement procedure. In order to test its overall performance, an experimental study wit...

Convolutional Radial Basis Function (RBF) networks are introduced for smoothing out irregularly sampled signals. Our proposed technique involves training a RBF network and then convolving it with a Gaussian smoothing kernel in an analytical manner. Since the convolution results in an analytic form, the computation necessary for numerical convolution is avoided. Convolutional RBF networks need t...

We describe a heuristic method for reconstructing a region in the plane from a noisy sample of points. The method uses radial basis functions with Gaussian kernels to compute a fuzzy membership function which provides an implicit approximation for the region.

We propose the concept of using superconducting quantum interferometers for the implementation of neural network algorithms with extremely low power dissipation. These adiabatic elements are Josephson cells with sigmoid- and Gaussian-like activation functions. We optimize their parameters for application in three-layer perceptron and radial basis function networks.