Performance Analysis of Evolving Fuzzy Neural Networks for Pattern Recognition

• Autores: Ronei Marcos De Moraes
• Localización: Mathware & soft computing: The Magazine of the European Society for Fuzzy Logic and Technology, ISSN-e 1134-5632, Vol. 20, Nº. 1, 2013, págs. 63-69
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • The Evolving Fuzzy Neural Networks (EFuNNs), recently proposed by Kasabov are dynamic connectionist feed forward networks with five layers of neurons and they are adaptive rule-based systems. Several paper can be found in the literature comparing EFuNN with other methods. However, it is known that results of all pattern recognition methods depend on the training data and in particular from statistical distribution of training data. This work assesses the accuracy of EFuNNs) for pattern recognition tasks using seven different statistical distributions data. Results of assessment are provided and show different accuracy according to the statistical distribution of data.