Evolving simple feed-forward and recurrent ANNs for signal classification: A comparison

Created by W.Langdon from gp-bibliography.bib Revision:1.4221

  author =       "Daniel Rivero and Julian Dorado and Juan Rabufial and 
                 Alejandro Pazos",
  title =        "Evolving simple feed-forward and recurrent ANNs for
                 signal classification: A comparison",
  booktitle =    "International Joint Conference on Neural Networks,
                 IJCNN 2009",
  year =         "2009",
  pages =        "2685--2692",
  address =      "Atlanta, Georgia, USA",
  month =        jun # " 14-19",
  keywords =     "genetic algorithms, genetic programming, evolutionary
                 computation, feedforward neural nets, learning
                 (artificial intelligence), recurrent neural nets,
                 signal classification, EEG signals, classification
                 tasks, epileptic seizures, evolutionary method, machine
                 learning, parameter configurations, recurrent ANN,
                 signal classification, simple feedforward ANN",
  DOI =          "doi:10.1109/IJCNN.2009.5178621",
  abstract =     "Among all of the Machine Learning techniques used for
                 classification tasks, Artificial Neural Networks (ANNs)
                 have obtained much success in their applications.
                 However, their development usually requires a manual
                 effort from the human expert in which several parameter
                 configurations (architectures, training parameters,
                 etc) are tried. This paper proposes a new evolutionary
                 method that evolves ANNs without any participation from
                 the human expert. This system can be used to evolve
                 feed-forward and recurrent ANNs. A real-world problem
                 has been used to test the behaviour of this system:
                 detection of epileptic seizures in EEG signals. A
                 comparison of the results obtained using recurrent and
                 feedforward ANNs to solve this problem is presented in
                 this paper. This comparison shows the good accuracies
                 obtained by this method (almost 100percent). Moreover,
                 these results show an important feature: the system
                 tries to evolve simple ANNs, with a low number of
                 neurons and connections (in many cases, the networks
                 have only 1 hidden neuron).",
  notes =        "also known as \cite{5178621}",

Genetic Programming entries for Daniel Rivero Cebrian Julian Dorado Juan Rabufial Alejandro Pazos Sierra