Artificial Neural Networks
Approximation and Learning Theory
Published on 5. November 1992
Book
Hardback
320 pages
978-1-55786-329-4 (ISBN)
Description
The recent re-emergence of network-based approaches to artificial intelligence has been accomplished by a virtual explosion of research. This research spans a range of disciplines - cognitive science, computer science, biology, neuroscience, electrical engineering, psychology, econometrics, philosophy, etc. which is, perhaps, wider than any other contemporary endeavour. Of all the contributing disciplines, the relatively universal language of mathematics provides some of the most powerful tools for answering fundamental questions about the capabilities and limitations of these `artificial neural networks'. In this collection, Halbert White and his colleagues present a rigorous mathematical analysis of the approximation and learning capabilities of the leading class of single hidden layer feedforward networks. Drawing together work previously scattered in space and time, the book gives a unified view of network learning not available in any other single location, and forges fundamental links between network learning and modern mathematical statistics.
More details
Language
English
Place of publication
Oxford
United Kingdom
Publishing group
John Wiley and Sons Ltd
Target group
College/higher education
Professional and scholarly
Illustrations
17 figures, 10 tables
Dimensions
Height: 229 mm
Width: 152 mm
Weight
613 gr
ISBN-13
978-1-55786-329-4 (9781557863294)
Copyright in bibliographic data is held by Nielsen Book Services Limited or its licensors: all rights reserved.
Schweitzer Classification
Content
Part 1 Approximation theory: there exists a neural network that does not make avoidable mistakes, A.R. Gallant and H. White; multilayer feedforward networks are universal approximators, K. Hornik, et al; universal approximation using feedforward networks with non-sigmoid hidden layer activation functions, M. Stinchcombe and H. White; approximating and learning unknown mappings using multilayer feedwork networks with bounded weights, M. Stinchcombe and H. White; universal approximation of an unknown mapping and its derivatives, K. Hornik, et al. Part 2 Learning and statistics: neural network learning and statistics, H. White; learning in artificial neural networks, H. White; some asymptotic results for learning in single hidden layer feedforward networks, H. White; connectionist nonparametric regression, H. White; nonparametric estimation of conditional quantiles using neural networks; on learning the derivatives of an unknown mapping with multilayer feedforward netowrks, A.R. Gallant and H. White; consequences and detection of misspecified nonlinear regression models, H. White; maximum likelihood estimation of misspecified models, H. White; some results for sieve estimation with dependent observations, H. White and J. Wooldridge.