RADIOELECTRONIC AND COMPUTER SYSTEMS

The subject of study in this article is the features of structural organization and functioning of the improved Hamming network as a model of neural network heteroassociative memory for classification by discriminant functions. The goal is to improve the neural network classifier based on the Hamming network, which implements the criterion of maximum similarity using discriminant functions and does not have restrictions on the representation of input data (not only binary data). The tasks: analyze the capabilities of associative memory models using neural networks as an example; analyze the features of classification on the principles of discriminant analysis; develop the structure of a neural network classifier as a model of neural network heteroassociative memory; perform simulation modeling of the classification process on the example of medical diagnosis. The methods used are a mathematical model of the functioning of a neural network as a classifier, and simulation in C#. The following results have been obtained: the structure of the neural network classifier has been improved through the formation connection matrix of a hidden layer from pre-calculated coefficients of linear discriminant functions, and the connection matrix of the output layer in the form symmetrical matrix with zeros on the main diagonal. This allows not only to simplify m connections, where m is the number of classes, in the structure of the output layer of the neural network classifier, but also to speed up the classification process, as well as to implement classification by the maximum of discriminant functions. Conclusions. The scientific novelty of the results obtained is as follows: the neural network classification method has been improved using pre-calculated elements of the connection matrices in the hidden and output layers of the classifier, which does not imply a long process of direct neural network learning with using discriminant functions; the structural organization of a neural network classifier is proposed, which is an improvement of the Hamming network as a model of heteroassociative memory, that allows using this classifier in a decision support system for medical diagnosis; the removal of positive feedback in neurons of the competitive (output) layer is implemented, which allows not only simplifies the structure of the neural network classifier but also speeds up the classification process almost 2 times, which is confirmed by the simulation results.

heteroassociative memory; neural network classifier; classification; linear discriminant function

Haykin, S. Neural Networks, A Comprehensive Foundation. Second ed. Prentice Hall, Upper Saddle River, New Jersey, 1999. 842 p.

Callan, R. The Essence of Neural Networks. Prentice Hall Europe, 1999. 232 p.

Jankowski, S., Lozowski, A., Zurada, J. M. Complex-valued multistate neural associative memory. IEEE Transactions on Neural Networks, 1996, vol. 7, no. 6, pp. 1491-1496. DOI: 10.1109/72.548176.

Wang, Jin-Hui. Associative Memory Cells: Basic Units of Memory Trace. Edition: 1. St. Publisher: Springer Nature, 2019. 484 p. DOI: 10.1007/978-981-13-9501-7.

Kryzhanovsky, B. V., Litinskii, L. B., Mikaelian, A. L. Vector-neuron models of associative memory. 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541). Budapest, 2004. DOI: 10.1109/IJCNN.2004.1380051.

Shoba, Rani1., Rao, D. Nagendra., Vatsal, Srinivasan. Review on neural networks associative memory models. International Journal of Pure and Applied Mathematics, 2018, vol. 120, no. 6, pp. 3143-3154.

Tyulmankov, Danil., Fang, Ching., Vadaparty, Annapurna., Yang, Guangyu Robert. Biological learning in key-value memory networks. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), 2021. 12 p.

Alhadi, Nisreen Abd., Kareem, Emad Abdul. Novel Hetero-Associative Memory: A Modified Bidirectional Associative Memory. International Journal of Engineering Research and Advanced Technology, 2016, vol. 2, no. 2. 15 p.

Souza, A. C., Valle, M. E. Generalized Exponential Bidirectional Fuzzy Associative Memory with Fuzzy Cardinality-Based Similarity Measures Applied to Face Recognition. Sociedade Brasileira de Matematica Aplicada e Computacional, 2018, vol. 18, no. 2, pp. 221-223. DOI: 10.5540/tema.2018.019.02.0221.

Moskalenko, V. V., Zarets'kyy, M. O., Koval's'kyy, Ya. Yu., Martynenko, S. S. Model' i metod navchannya klasyfikatora kontekstiv sposterezhennya na zobrazhennyakh videoinspektsiyi stichnykh trub [Model and method of training the classifier of observation contexts on video inspection images of sewer pipes]. Radioelektronni i komp'uterni sistemi – Radioelectronic and computer systems, 2020, no. 3, pp. 59-66. DOI: 10.32620/reks.2020.3.06.

Moskalenko, V. V., Zarets'kyy, M. O., Moskalenko, A. S., Korobov, A. G., Koval's'kyy, Ya. Yu. Bahatoetapnyy metod hlybynnoho navchannya z poperednim samonavchannyam dlya klasyfikatsiynoho analizu defektiv stichnykh trub [Multi-stage deep learning method with self-supervised pretraining for sewer pipe defects classification]. Radioelektronni i komp'uterni sistemi – Radioelectronic and computer systems, 2021, no. 4, pp. 71-81. DOI: 10.32620/reks.2021.4.06.

Martyniuk, T. B., Kozhemiako, A. V., Kupershtein, L. M., Homyuk, V. V., Mohamed Salem Nasser Mohamed, Smolarz, Andrzej, Kozbakova, Ainur. Neural network approach to numeric array sorting. Proceedings of SPIE: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments (6 November 2019), 2019, vol. 11176, article no. 111761N. DOI: 10.1117/12.2535916.

Martyniuk, T. B. Structure of Associative Processor with Bitwise Serial Processing of Data. Engineering Simulation, 1997, no. 14, pp. 383-389.

Karp, V. P. Intellektual'nyi analiz dannykh v probleme postroeniya reshayushchikh pravil klassifikatsii (na primere meditsinskoi diagnostiki) [Data mining in the problem of constructing decisive classification rules (on the example of medical diagnostics)]. Novosti iskusstvennogo intellekta, 2006, no. 2, pp. 57-75.

Martyniuk, T. B., Kupershtein, L. M. Medvid, A. V., Kozhemiako, A. V., Wojcik, W., Yuchshenko, O. Applications of Discriminant Analysis Methods in Medical Diagnostics. Proceedings of SPIE, Optical Fibers and Their Applications, 2012, vol. 8698, article no. 86980G. DOI: 10.1117/12.2019733.

Rangayyan, Rangaraj M. Biomedical Signal Analysis. Second ed. Wiley-IEEE Press, 2015. 720 p.

Yunkerov, V. I, Grigor'ev, S. G. Matematiko – statisticheskaya obrabotka dannykh meditsinskikh issledovanii [Mathematical and statistical processing of medical research data]. SPb., VMedA Publ., 2002. 266 p.

Shepelev, I. E., Vladimirskii, B. M. Postroenie neirosetevogo klassifikatora dlya interfeisa «mozg-komp'yuter» [Building a neural network classifier for the «brain-computer interface»]. Neirokomp'yutery: razrabotka, primenenie, 2010, no. 9, pp. 4-10.

Kupershtein, L., Martyniuk, T., Voitovych, O., Krentsin, M. Neural network approach in the stroke diagnosis. Proceedings of the 2016 IEEE 1st International Conference on Data Mining and Processing, DSMP 2016, 23-27 Aug., 2016. DOI: 10.1109/DSMP.2016.7583525.

Kupershtein, L., Martyniuk, T., Krentsin, M., Kozhemiako, A., Bezsmertna, H., Bezsmertnyi, Y., Smolarz, A., Kolimoldayev, M., Uvaysova, S., Weryńska-Bieniasz, R. Neural expert decision support system for stroke diagnosis. Proceedings of Conference: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments, Aug., 2017, vol. 10445, article no. 104453I. DOI: 10.1117/12.2280956.

Aldape-Pérez, M., Yáñez-Márquez, C., Camacho-Nieto, O., Argüelles-Cruza, A. J. An associative memory approach to medical decision support systems. Computer Methods and Programs in Biomedicine, 2012, vol. 106, no. 3, pp. 287-307. DOI: 10.1016/j.cmpb.2011.05.002.

Yang, Xiaozhou. Linear Discriminant Analysis, Explained. Available at: https://towardsdatascience.com/linear-discriminant-analysis-explained-f88be6c1e00b (аccessed 5.10.2020).

Brownlee, Jason. Linear Discriminant Analysis for Machine Learning. Available at: https://machinelearningmastery.com/linear-discriminant-analysis-for-machine-learning/ (accessed 15.11.2020).

Semeriakova, E. G., Berestneva, O. G., Makarova, L. S. Matematicheskie metody v zadachakh meditsinskoi diagnostiki [Mathematical methods in problems of medical diagnostics]. Modern problems of science and education, 2012, no. 6, pp. 29.