Neural information processing models largely assume that the samples for training a neural network are sufficient. Otherwise there exist a non-negligible error between the real function and estimated function from a trained network. To reduce the error in this paper we suggest a diffusion-neural-network (DNN) to learn from a small sample. First, we show the principle of information diffusion us...

Fraud is a common phenomenon in business, and according to Section 24 of the Iranian Auditing Standards, it is the fraudulent act of one or more managers, employees, or third parties to derive unfair advantage and any intentional or unlawful conduct. Financial statements are a means of transmitting confidential management information about the<br ...

A three-hidden-layer neural network with super approximation power is introduced. This built the floor function (⌊x⌋), exponential (2x), step (1x≥0), or their compositions as activation in each neuron and hence we call such networks Floor-Exponential-Step (FLES) networks. For any width hyper-parameter N∈N+, it shown that FLES max{d,N} three hidden layers can uniformly approximate a Hölder conti...

In this article we present the multivariate approximation of time splitting random functions defined on a box or RN,N∈N, by neural network operators quasi-interpolation type. We achieve these approximations obtaining quantitative-type Jackson inequalities engaging modulus continuity related function its partial high-order derivatives. use density to define our operators. These derive from logis...

This paper proposes a comparison between wavelet neural networks (WNN), RBF neural network and polynomial approximation in term of 1-D and 2-D functions approximation. We present a novel wavelet neural network, based on Beta wavelets, for 1-D and 2-D functions approximation. Our purpose is to approximate an unknown function f: Rn R from scattered samples (xi; y = f(xi)) i=1....n, where first, w...

Conventional quaternion based methods have been extensively employed for spacecraft attitude control where the aerodynamic forces can be neglected. In the presence of aerodynamic forces, the flight attitude control is more complicated due to aerodynamic moments and inertia uncertainties. In this paper, a robust nero-adaptive quat...

The value algorithms of classical function approximation theory have a common drawback: the compute-intensive, poor adaptability, high model and data demanding and the limitation in practical applications. Neural network can calculate the complex relationship between input and output, therefore, neural network has a strong function approximation capability. This paper describes the application ...