P. Ciotirnae

Learn More
The efficiency of pattern recognition (PR) systems using RBF neural networks to implement their recognition function, depends a lot by the training algorithms of these neural networks and especially, by the specific techniques (e.g., supervised, clustering techniques etc.) used for RBF center positioning. Having as starting point the basic property of(More)
It is well known that the design and effective development of ATTR systems incorporating in their architecture some characteristic elements belong to artificial intelligence represents and will represent a very important research direction in this area. Accordingly, in the current study a specific design algorithm for a full neural implementation of an ATTR(More)
  • 1