Semantic Learning Machine: A Feedforward Neural Network Construction Algorithm Inspired by Geometric Semantic Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@InProceedings{conf/epia/GoncalvesSF15,
  author =       "Ivo Goncalves and Sara Silva and Carlos M. Fonseca",
  title =        "Semantic Learning Machine: {A} Feedforward Neural
                 Network Construction Algorithm Inspired by Geometric
                 Semantic Genetic Programming",
  booktitle =    "Progress in Artificial Intelligence - 17th Portuguese
                 Conference on Artificial Intelligence, {EPIA} 2015",
  year =         "2015",
  editor =       "Francisco C. Pereira and Penousal Machado and 
                 Ernesto Costa and Amilcar Cardoso",
  volume =       "9273",
  series =       "Lecture Notes in Computer Science",
  pages =        "280--285",
  address =      "Coimbra, Portugal",
  month =        sep # " 8-11",
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming",
  isbn13 =       "978-3-319-23484-7",
  bibdate =      "2015-08-26",
  bibsource =    "DBLP,
                 http://dblp.uni-trier.de/db/conf/epia/epia2015.html#GoncalvesSF15",
  URL =          "http://dx.doi.org/10.1007/978-3-319-23485-4",
  DOI =          "doi:10.1007/978-3-319-23485-4_28",
  size =         "6 pages",
  abstract =     "Geometric Semantic Genetic Programming (GSGP) is a
                 recently proposed form of Genetic Programming in which
                 the fitness landscape seen by its variation operators
                 is unimodal with a linear slope by construction and,
                 consequently, easy to search. This is valid across all
                 supervised learning problems. In this paper we propose
                 a feedforward Neural Network construction algorithm
                 derived from GSGP. This algorithm shares the same
                 fitness landscape as GSGP, which allows an efficient
                 search to be performed on the space of feedforward
                 Neural Networks, without the need to use
                 backpropagation. Experiments are conducted on real-life
                 multidimensional symbolic regression datasets and
                 results show that the proposed algorithm is able to
                 surpass GSGP, with statistical significance, in terms
                 of learning the training data. In terms of
                 generalization, results are similar to GSGP.",
}

Genetic Programming entries for Ivo Goncalves Sara Silva Carlos M Fonseca

Citations