Please use this identifier to cite or link to this item:
logo share SHARE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

Neural modules: networks with constrained architectures for nonlinear function identification

AuthorsMorcego, Bernardo; Fuertes Armengol, Jose Mª; Cembrano, Gabriela CSIC ORCID
KeywordsConstrained architectures
Neural modules
Nonlinear function identification
Structural complexity
Structural constraints
Training cost
Control theory
Issue Date1996
PublisherInstitute of Electrical and Electronics Engineers
CitationInternational Workshop on Neural Networks for Identification, Control, Robotics, and Signal/Image Processing: 290-298 (1996)
AbstractThe aim of this work is the design of a class of neural networks for nonlinear function identification: the so-called neural modules. A neural module is a neural network with an internal structure specially designed to be able to learn and mimic the behaviour of a certain class of dynamic systems. Neural networks are abstract models well suited for approximating nonlinear functions. The training cost and the structural complexity of neural networks can be drastically reduced if a-priori knowledge of the function to be learned is internally incorporated in the form of structural constraints. The resulting neural network has less parameters than a conventional one, much faster learning convergence and it can provide meaningful information about the learned nonlinear function. This paper describes the design of a useful set of neural modules for system identification and gives general guidelines for the design of neural modules. The resulting networks are evaluated and their use on general systems identification is pointed out.
DescriptionInternational Workshop on Neural Networks for Identification, Control, Robotics, and Signal/Image Processing (NICROSP), 1996, Venecia (Italia)
Appears in Collections:(IRII) Comunicaciones congresos

Files in This Item:
File Description SizeFormat
doc1.pdf556,49 kBAdobe PDFThumbnail
Show full item record
Review this work

Page view(s)

checked on May 16, 2022


checked on May 16, 2022

Google ScholarTM




WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.