APPLICATION OF A NEURO NETWORK APPROACH TO LOGICAL DATA PROBLEMS AND BUILDING INTELLIGENT DECISION-MAKING SYSTEMS

The need to reduce the dimensionality of large data sets while maintaining the logical structure, as well as the detection of hidden patterns and the removal of information noise and redundancy in the description of diagnostic (recognition) objects leads to the need to construct an effective method for classifying objects in weakly formalized areas of knowledge. Logical functions that describe objects using variable-valued predicates allow us to reveal hidden regularities and eliminate redundancy in the description of objects. Ordered by means of variable-valued logical functions, object classes are the basis for the formation of the structure of cognitive maps. The purpose of this study is to create an algorithm for constructing a logical neural network based on the variable-valued logic function and justifying the possibility of applying the results obtained in the construction of cognitive maps. The theoretical possibility and algorithms allowing to make the transition from variable-valued logic functions to cognitive maps using the neural network approach are grounded. The result of this work is the procedure for constructing a cognitive map using logical neural networks built on the basis of variable-valued logical functions. The advantage of the obtained cognitive map is the possibility of functioning within the framework of fuzzy logic.

1. Axelrod R., The structure of Decision: Cognitive Maps of Political Elites. Princeton University Press, 1976. — 321 с.

2. Carvahlo J.P., Tome J.A.B., Rule Based Cognitive Maps — A comparison with fuzzy Cognitive Maps//Proceedings of the NAFIPS99, 1999. — 32 с

3. Lyutikova L.A., Timofeev A.V., Sgurev V.V., Jocov V.I Razvitie i primenenie mnogoznachnyh logik i setevyh potokov v intellektual'nyh sistemah. // Trudy SPIIRAN, vyp. 2, 2005. S. 114–126

4. Lyutikova L.A. Modelirovanie i minimizaciya baz znanij v terminah mnogoznachnoj logiki predikatov. Nal'chik. – Preprint, 2006. 33 s.

5. Timofeev A.V., Kosovskaya T.M. Nejrosetevye metody logicheskogo opisaniya i raspoznavaniya slozhnyh obrazov // Trudy SPIIRAN. 2013. Vyp. 27. C. 144- 155.

6. SHibzuhov Z.M. Konstruktivnye metody obucheniya nejronnyh setej. M.: Nauka, 2006. 159 s.

7. Jürgen Schmidhuber Deep learning in neural networks: An overview Neural Networks Volume 61, January 2015, Pages 85–117

8. Barskij A.B. Logicheskie nejronnye seti. INTUIT; BINOM, 2007. 352 s.

9. Dimitrichenko D. P. Primenenie peremennoznachnyh logicheskih funkcij i nejronnyh setej v sistemah prinyatiya reshenij // Vestnik KRAUNC. Fiz.-mat. nauki. 2016. № 4-1(16). C. 93-100.

10. Dimitrichenko D.P. Ispol'zovanie nejronnyh setej dlya povysheniya ehffektivnosti peremennoznachnyh logicheskih funkcij // Vestnik IrGTU. №10 (105), 2015. S. 12-16.

11. ZHilov R.A., Optimizaciya kognitivnoj karty dlya zadach prognozirovaniya. // Kibernetika i programmirovanie. 2015. № 5. S.128-135