Thesis (Ph. D.)--University of Hawaii at Manoa, 1992.Includes bibliographical references (leaves 144-148)Microfiche.xiii, 148 leaves, bound ill. 29 cmThis dissertation analyzes the effect of different characteristics of data on the training and estimation accuracy of neural networks. The literature on the universal approximation property of neural networks is reviewed. An examination of the relationship of the neural network approach to traditional statistical methods of approximation brought about proposed enhancements to the neural network training procedure. The study generated data samples characterized by different functional forms, levels of random noise, number and magnitude of outliers, and strength of multicollinearity. These sampl...
Inspired by biological neural networks, Artificial neural networks are massively parallel computing ...
Abstract. Noise disturbance in training data prevents a good approxi-mation of a function by neural ...
The paper discusses issues connected with the use of an artificial neural network (ANN) to approxima...
AbstractIn this work, some ubiquitous neural networks are applied to model the landscape of a known ...
The focus of this paper is on the neural network modelling approach that has gained increasing recog...
In this paper, we present a review of some recent works on approximation by feedforward neural netwo...
We review the use of global and local methods for estimating a function mapping R m ) R n from s...
We review the use of global and local methods for estimating a function mapping from samples of the ...
The focus of this paper is on the neural network modelling approach that has gained increasing recog...
Neural networks provide a more flexible approximation of functions than traditional linear regressio...
In the modern IT industry, the basis for the nearest progress is artificial intelligence technologie...
Approximation of high-dimensional functions is a challenge for neural networks due to the curse of d...
Capabilities of linear and neural-network models are compared from the point of view of requirements...
This paper applies a recently developed neural network called plausible neural network (PNN) to func...
Approximation of highly nonlinear functions is an important area of computational intelligence. The ...
Inspired by biological neural networks, Artificial neural networks are massively parallel computing ...
Abstract. Noise disturbance in training data prevents a good approxi-mation of a function by neural ...
The paper discusses issues connected with the use of an artificial neural network (ANN) to approxima...
AbstractIn this work, some ubiquitous neural networks are applied to model the landscape of a known ...
The focus of this paper is on the neural network modelling approach that has gained increasing recog...
In this paper, we present a review of some recent works on approximation by feedforward neural netwo...
We review the use of global and local methods for estimating a function mapping R m ) R n from s...
We review the use of global and local methods for estimating a function mapping from samples of the ...
The focus of this paper is on the neural network modelling approach that has gained increasing recog...
Neural networks provide a more flexible approximation of functions than traditional linear regressio...
In the modern IT industry, the basis for the nearest progress is artificial intelligence technologie...
Approximation of high-dimensional functions is a challenge for neural networks due to the curse of d...
Capabilities of linear and neural-network models are compared from the point of view of requirements...
This paper applies a recently developed neural network called plausible neural network (PNN) to func...
Approximation of highly nonlinear functions is an important area of computational intelligence. The ...
Inspired by biological neural networks, Artificial neural networks are massively parallel computing ...
Abstract. Noise disturbance in training data prevents a good approxi-mation of a function by neural ...
The paper discusses issues connected with the use of an artificial neural network (ANN) to approxima...