Artificial Neural Network as Universal Approximation of Nonlinear Relations
Result description
The layered neural networks are still considered as very general tools for approximation and they became popular especially for their simple implementation. The practical usage is, however, nontrivial in the choice of an appropriate architecture. The presented contribution is concerned with the development of a simple neural network with the selfadaptive architecture, which can enable easier neural network applications in engineering problems. Its approximation abilities are tested on several mathematical problems and two different modes of material parameters' identification problem. In the first one, the neural network is used to approximate the numerical model predicting the response for a given set of material parameters and loading. The second mode employs the neural network for constructing an inverse model, where material parameters are directly predicted for a given (measured) response.
Keywords
artificial neural networkmulti-layer perceptronapproximationnonlinear relationsback-propagationparameter identification
The result's identifiers
Result code in IS VaVaI
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Artificial Neural Network as Universal Approximation of Nonlinear Relations
Original language description
The layered neural networks are still considered as very general tools for approximation and they became popular especially for their simple implementation. The practical usage is, however, nontrivial in the choice of an appropriate architecture. The presented contribution is concerned with the development of a simple neural network with the selfadaptive architecture, which can enable easier neural network applications in engineering problems. Its approximation abilities are tested on several mathematical problems and two different modes of material parameters' identification problem. In the first one, the neural network is used to approximate the numerical model predicting the response for a given set of material parameters and loading. The second mode employs the neural network for constructing an inverse model, where material parameters are directly predicted for a given (measured) response.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2010
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of International Conference on Modelling and Simulation 2010 in Prague
ISBN
978-80-01-04574-9
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
—
Publisher name
České vysoké učení technické v Praze
Place of publication
Praha
Event location
Praha
Event date
Jun 22, 2010
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—
Basic information
Result type
D - Article in proceedings
CEP
JD - Use of computers, robotics and its application
Year of implementation
2010