Solving differential equations with constructed neural networks

Created by W.Langdon from gp-bibliography.bib Revision:1.4524

  author =       "Ioannis G. Tsoulos and Dimitris Gavrilis and 
                 Euripidis Glavas",
  title =        "Solving differential equations with constructed neural
  journal =      "Neurocomputing",
  volume =       "72",
  number =       "10-12",
  pages =        "2385--2391",
  year =         "2009",
  note =         "Lattice Computing and Natural Computing (JCIS 2007) /
                 Neural Networks in Intelligent Systems Designn (ISDA
  ISSN =         "0925-2312",
  DOI =          "doi:10.1016/j.neucom.2008.12.004",
  URL =          "",
  keywords =     "genetic algorithms, genetic programming, Differential
                 equations, Neural networks, Grammatical evolution",
  abstract =     "A novel hybrid method for the solution of ordinary and
                 partial differential equations is presented here. The
                 method creates trial solutions in neural network form
                 using a scheme based on grammatical evolution. The
                 trial solutions are enhanced periodically using a local
                 optimisation procedure. The proposed method is tested
                 on a series of ordinary differential equations, systems
                 of ordinary differential equations as well as on
                 partial differential equations with Dirichlet boundary
                 conditions and the results are reported.",

Genetic Programming entries for Ioannis G Tsoulos Dimitris Gavrilis Euripidis Glavas