Research Article Open Access

Adaptive Resonance Theory 1 (ART1) Neural Network Based Horizontal and Vertical Classification of 0-9 Digits Recognition

Mbaitiga Zacharie

Abstract

This study describes the Adaptive Resonance Theory 1 (ART1), an efficient algorithm that emulates the self-organizing pattern recognition and hypothesis testing properties of the ART neural network architecture for horizontal and vertical classification of 0-9 digits recognition. In our approach the ART1 model can self-organize in real time producing stable and clear recognition while getting input patterns beyond those originally stored. It can also preserve its previously learned knowledge while keeping its ability to learn new input patterns that can be saved in such a fashion that the stored patterns cannot be destroyed or forgotten. A parameter called the attentional vigilance parameter determines how fine the categories will be. If vigilance increases or decreases due to environmental control feedback, then the system automatically searches for and learns fine recognition categories.

Journal of Computer Science
Volume 3 No. 11, 2007, 869-873

DOI: https://doi.org/10.3844/jcssp.2007.869.873

Submitted On: 15 September 2007 Published On: 30 November 2007

How to Cite: Zacharie, M. (2007). Adaptive Resonance Theory 1 (ART1) Neural Network Based Horizontal and Vertical Classification of 0-9 Digits Recognition . Journal of Computer Science, 3(11), 869-873. https://doi.org/10.3844/jcssp.2007.869.873

  • 3,329 Views
  • 5,257 Downloads
  • 4 Citations

Download

Keywords

  • ART1
  • gain control
  • input pattern
  • signal