• DocumentCode
    2350957
  • Title

    Optimization of the combinatorial neural model

  • Author

    Beckenkamp, Fábio Ghignatti ; Feldens, Miguel Artur ; Pree, Wolfgang

  • Author_Institution
    Software Eng. Group, Constance Univ., Germany
  • fYear
    1998
  • fDate
    9-11 Dec 1998
  • Firstpage
    49
  • Lastpage
    54
  • Abstract
    We present significant optimization of the so-called combinatorial neural model (CNM). CNM is a hybrid (neural/symbolic) model that has been used in areas such as expert system development and data mining. The paper first explains the CNM architecture and then presents CNM optimization together with empiric results. The most important optimization aims at taming combinatorial explosion, which is the main problem inherent to this model
  • Keywords
    feedforward neural nets; learning (artificial intelligence); neural net architecture; optimisation; architecture; combinatorial neural model; data mining; expert system; feedforward neural networks; incremental learning; optimization; symbolic model; Capacity planning; Computer science; Data mining; Expert systems; Explosions; Fuzzy sets; Java; Neural networks; Neurons; Software engineering;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1998. Proceedings. Vth Brazilian Symposium on
  • Conference_Location
    Belo Horizonte
  • Print_ISBN
    0-8186-8629-4
  • Type

    conf

  • DOI
    10.1109/SBRN.1998.730993
  • Filename
    730993