Graph genetic programming for hybrid neural networks design

L. Ferariu, B. Burlacu

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

Abstract

This paper presents a novel approach devoted to the design of feed forward hybrid neural models. Graph genetic programming techniques are used to provide a flexible construction of partially interconnected neural structures with heterogeneous layers built as combinations of local and global neurons. By exploiting the inner modularity and the parallelism of the neural architectures, the approach suggests the encryption of the potential mathematical models as directed acyclic graphs and defines a minimally sufficient set of functions which guarantees that any combination of primitives encodes a valid neural model. The exploration capabilities of the algorithm are heightened by means of customized crossovers and mutations, which act both at the structural and the parametric level of the encrypted individuals, for producing offspring compliant with the neural networks' formalism. As the parameters of the models become the parameters of the primitive functions, the genetic operators are extended to manage the inner configuration of the functional nodes in the involved hierarchical individuals. The applicability of the proposed design algorithm is discussed on the identification of an industrial nonlinear plant.

Original languageEnglish
Title of host publicationICCC-CONTI 2010 - IEEE International Joint Conferences on Computational Cybernetics and Technical Informatics, Proceedings
Pages547-552
Number of pages6
DOIs
Publication statusPublished - 2010
Externally publishedYes
EventIEEE International Joint Conferences on Computational Cybernetics and Technical Informatics, ICCC-CONTI 2010 - Timisoara, Romania
Duration: 27 May 201029 May 2010

Publication series

NameICCC-CONTI 2010 - IEEE International Joint Conferences on Computational Cybernetics and Technical Informatics, Proceedings

Conference

ConferenceIEEE International Joint Conferences on Computational Cybernetics and Technical Informatics, ICCC-CONTI 2010
CountryRomania
CityTimisoara
Period27.05.201029.05.2010

Fingerprint Dive into the research topics of 'Graph genetic programming for hybrid neural networks design'. Together they form a unique fingerprint.

Cite this