Abstract: A model of self-modificated predicate network with cells implementing predicate formulas in the form of elementary conjunction is suggested. Unlike a classical neuron network the proposed model has two blocks: a training block and a recognition block. If a recognition block has a mistake then the control is transferred to a training block. Always after a training block run the configuration of a recognition block is changed. The base of the proposed predicate network is logic-objective approach to AI problems solving and level description of classes.

Keywords: artificial intelligence, pattern recognition, predicate calculus, level description of a class.

ACM Classification Keywords: I.2.4 Artificial Intelligence - Knowledge Representation Formalisms and Methods-- Predicate logic; I.5.1 Pattern Recognition Models – Deterministic; F.2.2 Nonnumerical Algorithms and Problems – Complexity of proof procedures.

Link:

SELF-MODIFICATED PREDICATE NETWORKS

Tatiana Kosovskaya

http://www.foibg.com/ijita/vol22/ijita22-03-p03.pdf