# Testor and Logic Separation in Pattern Recognition

## Keywords:

Pattern recognition, Discrete analysis, Testor, Logic separation## Abstract

This article is an outline of the first steps of formation of the discrete analytical approach (DAA) of the theoretical pattern recognition (PR) founded by Yu. I. Zhuravlev [2,15]. The “first step” time period covers 1965-75. The DAA domain is further developed into a large number of models and algorithms [1-38]. Hundreds of candidate and tens of doctoral theses were defended in the topic, and thousands of scientific papers were published since then. The essence of DAA is that it is based on the well-developed theory of discrete mathematical analysis and so it is interpretable in terms of input data structures and relations. In parallel to this, several alternative directions such as statistical theory, neural networks, and the structural recognition theory were under development. Today the term machine learning integrates these directions and it appears more frequently. In addition, in pattern recognition area appeared frameworks such as the Deep Learning and Meta-Learning that address, correspondingly, the agile use of HPC and the learning of the learning issues. Deep Learning is based on Deep (multilayer) Neural Networks and so it inherits hardness of knowledge extraction and hardness of interpretability. Meta-Learning is a novel term but in its essence it was addressed in several discrete DAA researches. It is attractive to stay on analysis of the whole PR developments but the aim of our short essay is to compare two core elements of DAA believing that the classic knowledge and theory are enduring and that any further developments will use them in their constructions or in stages of evaluating the result.

## References

A. N. Dmitriev, Yu. I. Zhuravlev and F.P. Krendelev, “On mathematical principles of object and phenomena classification”, Discrete Analysis, Novosibirsk (In Russian), vol. 7, pp. 3-15, 1966.

Yu. I. Zhuravlev, Selected Scientific Works, (in Russian), Magistr, Moscow, 1998.

I. A. Chegis and S. V. Yablonskii, “Logical methods for controlling electrical systems”, Proceedings of Mathematical Institute after V. A. Steklov, Moscow (In Russian), vol. 51, pp. 270-360, 1958.

M. M. Bongard, Pattern Recognition, Rochelle Park, N.J., Hayden Book Co., Spartan Books, 1970. (Original publication: Проблема Узнавания, Nauka Press, Moscow, 1967).

M. A. Aizerman, E. M. Braverman and L. I. Rozenoer, Potential Functions Method in Learning of Machines, Moscow, Nauka, 1970.

M. N. Vaintsvaig, “Pattern Recognition Learning Algorithm KORA”, in Pattern recognition learning algorithms, Moscow, Sovetskoe Radio, pp.110-116, 1973.

S. V. Yablonskii, “Functional constructions in k-valued logic”, Proceedings of Mathematical Institute after V. A. Steklov, Moscow (In Russian), vol. 51, pp. 5-142, 1958.

Yu. I. Zhuravlev, “On separating subsets of vertices of n-dimensional unit cube”, Proceedings of Mathematical Institute after V. A. Steklov, vol. 51, pp. 143-157, 1958.

L.V. Baskakova and Yu.I. Zhuravlev, “Model of recognition algorithms with representative and support sets”, Journal of Comp. Math. and Math. Phys., vol. 21, no.5, pp. 1264-1275, 1981.

Yu. I. Zhuravlev, “On an algebraic approach to the problems of pattern recognition and classification”, Problemy Kybernetiki, vol. 33, pp.5-68, 1978.

Yu. I. Zhuravlev and V. V. Nikiforov, “Recognition algorithms based on calculation of estimates”, Cybernetics, vol. 3, pp.1-11, 1971.

L. H. Aslanyan, “On a pattern recognition method based on the separation by the disjunctive normal forms”, Kibernetika, vol. 5, pp. 103 -110, 1975.

V. N. Vapnik and A. Ya. Chervonenkis, Theory of Pattern Recognition, Moscow, Nauka, 1974.

Yu. I. Zhuravlev, Correct Algebras Over the Sets of Incorrect (Heuristical) Algorithms, I, Cybernetics, no.4, 1977,

L. H. Aslanyan and Yu. I. Zhuravlev, “Logic separation principle”, Computer Science & Information Technologies Conference, Yerevan, September 17-20, pp. 151-156, 2001.

Yu. I. Zhuravlev and K. V. Rudakov, “On algebraic corrections of procedures of maintenance of information”, in Problems of Applied Mathematics and Informatics, pp. 187–198, 1987.

V. L. Matrosov, “Volume of algorithmic polynomials over the sets of calculation of estimates algorithms”, Journal of Comp. Math. and Math. Phys., vol. 25, no. 1, pp. 122– 133, 1985.

L. Aslanyan and J. Castellanos, “Logic based pattern recognition - ontology content (1)”, Proceedings iTECH-06, Varna, Bulgaria, , pp. 61-66, 2006.

L. Aslanyan and V. Ryazanov, “Logic based pattern recognition - ontology content (2)”, Information Theories and Applications, vol. 15, no. 4, pp. 314-318, 2008.

L. H. Aslanyan, “The discrete isoperimetry problem and related extremal problems for discrete spaces”, Problemy Kibernetiki, vol. 36, pp. 85-128, 1979.

L. Aslanyan and H. Sahakyan, “Chain Split and computations in practical rule mining”, Intenational Book Series, Information Science and Computing, Book 8, Classification, forecasting, Data Mining, pp. 132-135, 2009.

L. Aslanyan and H. Sahakyan, “Composite block optimized classification data structures”, International Book Series Information science and computing, book 16, New Trends in Classification and Data Mining, pp. 25-31, 2010.

Yu. I. Zhuravlev, “On algebraic approach to solve the problems of recognition and classification”, in Problemy Kibernetiki, Nauka, Moscow, vol. 33, pp. 5–68, 1978.

Yu. I. Zhuravlev, “Correct algebras for incorrect (Heuristic) sets of algorithms. I”, Kibernetika, no. 4, pp. 14–21 1977

Yu. A. Zuev, “Methods to improve the classification reliability in the presence of several classifiers, based on monotony principle”, Zh. Vychisl. Mat. Mat. Fiz., vol. 21, no. 1, pp. 157–167, 1981.

L. A. Aslanyan, L. F. Mingo, J. B. Castellanos, F. B. Chelnokov, A. A. Dokukin and V. V. Ryazanov, “On logical correction of neural network algorithms for pattern recognition”, International Journal Information Theories & Applications, vol. 14, pp. 203-205, 2007.

Yu. I. Zhuravlev, V. V. Ryazanov and O. V. Sen’ko, Recognition. Mathematical Methods. Program System. Practical Applications, (in Russian), Fazis, Moscow, 2006.

Yu. I. Zhuravlev and I. V. Isaev, “The way to generate the recognition algorithms, which are correct for the given control sample”, Zh. Vychisl. Mat. Mat. Fiz., vol. 19, no. 3, p.726-738, 1979.

V. V. Ryazanov, “Logical regularities in pattern recognition (parametric approach)”, Zh. Vychisl. Mat. Mat. Fiz., vol. 47, no. 10, pp. 1793-1808, 2007.

R. O. Duda and P. E. Hart, Pattern Recognition and Scene Analysis, John Willey, New York, 1973, Mir, Moscow, 1976.

J. Ruiz-Shulcloper and M. A. Abidi, “Logical combinatorial pattern recognition: A review”, Recent Research Developments in Pattern Recognition, Transworld Research Networks, Kerala, India, pp. 133-176, 2002.

C. J. C. Burges, “A tutorial on support vector machines for pattern recognition”, in Data Mining and Knowledge Discovery, vol. 2, pp. 121–167, 1998.

P. Wasserman, Neurocomputing: Theory and Practice, Van Nostrand Reinhold, New York, 1990, Mir, Moscow, 1992.

P. Horton and N. Kenta, “A probabilistic classification system for predicting the cellular localizations sites of proteins”, in Intelligent Sys. Mol. Biol., St. Lois, pp. 109–115, 1996.

O. L. Mangasarian and W. H. Wolberg, “Cancer diagnosis via linear programming”, SIAM News, vol. 23, no. 5, 1-18, 1990.

[Online]. Available: http://mlearn.ics.uci.edu/

[Online]. Available: http://www.machinelearning.ru/

V. G. Sigillito, S. P. Wing, L. V. Hutton, K. B. Baker, “Classification of radar returns from the ionosphere using neural networks”, Johns Hopkins APL Technical Digest, vol. 10, pp. 262–266. 1989.

Yu. I. Zhuravlev, “Correct algebras for incorrect (Heuristic) sets of algorithms, II, Kibernetika, no. 6 pp. 21-27 1977;

Yu. I. Zhuravlev, “Correct algebras for incorrect (Heuristic) sets of algorithms, III, Kibernetika, no. 2, pp. 35–43, 1978.

## Downloads

## Published

## How to Cite

*Mathematical Problems of Computer Science*,

*44*, 33–41. Retrieved from http://mpcs.sci.am/index.php/mpcs/article/view/180

## Issue

## Section

## License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.