FAST AUTOMATIC CONFIGURATION OF ARTIFICIAL NEURAL NETWORKS USED FOR BINARY PATTERNS RECOGNITION

Adrian Horzyk

Abstract


This paper prcsents a powcrful method of an automatically generated architccturc of ncural networks uscd for binary pattems rccognition, which can quickly and automatically rcducc synapses in a way of minimally reducing a quality of rccognition and a quality of generalization. Moreovcr, this method computes all weights in two runs over a leaming sequence, what makes this method vcry fast. First, the method calculatcs all binary featureś for each pattem and then weights are computcd. Furthcrmore, there is a quality of generalization considered because it is one o f the most important factors o f recognition whilc using neural networks.


Full Text:

PDF

References


Hertz J., Krogh A., Palmer R.: Introduction to the theory o f neural computation. Redwood City, Addison-Wesley Pubłishing Company, The Advanced Book Program

Horzyk A., Hybrid A.: Neural NetWork Usedfor the Color Conversionfrom RGB to

CMY and a New Methodfor Choosing a Learning Set. Bydgoszcz, Image Processing

& Communications, vol. 4, No. 1-2, ATR 1998

Tadeusiewicz R.: Sieci neuronowe. Warszawa, Akademicka Oficyna Wydawnicza

RM 1993

Tadeusiewicz R., Flasiński M.: Rozpoznawanie obrazów. Warszawa, PWN 1991

Zurada J., Barski M., Jędruch W.: Sztuczne sieci neuronowe. Warszawa, PWN 1996




DOI: https://doi.org/10.7494/csci.2001.3.1.3595

Refbacks

  • There are currently no refbacks.