Importance of information pre-processing importance in the improvement of neural networks results

  1. Menéndez, C. 1
  2. Ordieres, J.B. 1
  3. Ortega, F. 1
  1. 1 Universidad de Oviedo
    info

    Universidad de Oviedo

    Oviedo, España

    ROR https://ror.org/006gksa02

Revista:
International Journal of Expert Systems

ISSN: 0894-9077

Año de publicación: 1996

Volumen: 13

Número: 2

Páginas: 95-102

Tipo: Artículo

SCOPUS: 2-s2.0-0030141703 GOOGLE SCHOLAR

Otras publicaciones en: International Journal of Expert Systems

Resumen

This paper compares the success ratio of certain topologies when their input data are changed through different pre-processing methods. It begins with the database description, and it shows some different kinds of pre-processing that will be applied and the necessary modifications to the input layer of the network. The process is carried out using four networks with supervised learning (Standard Backpropagation, Quick propagation, Resilient Propagation and Backpropagation With Momentum) and two with unsupervised learning (ART 1 and Dynamic Learning Vector Quantization).