16+
DOI: 10.18413/2518-1092-2016-1-1-4-11

NEW ARCHITECTURES AND ALGORITMS OF TRAINING THE ADAPTIVE RESONANCE THEORY TO NEURAL NETWORKS

The article analyzes the advantages and disadvantages of architectures and algorithms of training the Adaptive Resonance Theory (ART) to discrete neural networks. The authors propose some new architectures of ART neural networks and training algorithms of these networks without adaptation of link weights of distributed recognizing neurons.
Number of views: 6038 (view statistics)
Количество скачиваний: 6665
Full text (HTML)Full text (PDF)To articles list
  • User comments
  • Reference lists

While nobody left any comments to this publication.
You can be first.

Leave comment: