Abstract: The paper is devoted to the description of hybrid pattern recognition method developed by research groups from Russia, Armenia and Spain. The method is based upon logical correction over the set of conventional neural networks. Output matrices of neural networks are processed according to the potentiality principle which allows increasing of recognition reliability.

Keywords: Pattern recognition, forecasting, neural networks, logical correction.

ACM Classification Keywords: I.2. Artificial Intelligence, I.5. Pattern Recognition, F.1.1 Models of Computation

Link:

ON LOGICAL CORRECTION OF NEURAL NETWORK ALGORITHMS FOR PATTERN RECOGNITION

Levon Aslanyan, Luis de Mingo, Juan Castellanos, Vladimir Ryazanov, Fedor Chelnokov, Alexander Dokukin

http://www.foibg.com/ijita/vol14/ijita14-3-p01.pdf