Abstract
The article considers the possibility of modeling artificial neural networks using the mathematical apparatus of information theory. The issues of pattern recognition, classification and clustering of images using neural networks are represented by two main architectures: a direct distribution network and convolutional networks. The possibility of using orthogonal transformations to increase the efficiency of neural networks, the use of wavelet transformations in convolutional networks is investigated. Based on the theoretical studies carried out, the directions on practical application of the obtained results are proposed.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kruglov VV, Borisov VV (2001) Artificial neural networks. Theory and practice. Hotline-telecom, p 382
McCulloch WS, Pitts Y (1956) A logical calculus of ideas related to nervous activity. In: Shannon CE, McCarthy J (ed) Automata. Publishing House of Foreign Literature, pp 363–384
Khaikin S (2008) Neural networks: a complete course, 2nd edn. Williams Publishing House
Kolmogorov AN (1957) On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition. Dokl Akad Nauk SSSR 114(5):953–956
Arnold VI (1958) On the representation of functions of several variables in the form of a superposition of functions of a smaller number of variables. Math Educ 3:41–61
Hecht-Nielsen R (1990) Neurocomputing. Addison-Wesely Publishing Company
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366
Shannon K (1963) Works on information theory and cybernetics. In: Dobrushin RL, Lupanov OB (eds) Per. with eng. Publishing House Foreign Literature
Vershkov NA, Kuchukov VA, Kuchukova NN, Babenko M (January 2020). The wave model of artificial neural network. In 2020 IEEE conference of Russian young researchers in electrical and electronic engineering (EIConRus). IEEE, pp 542–547
Vershkov NA, Babenko MG, Kuchukov VA, Kuchukova NN (2021) Advanced supervised learning in multi-layer perceptrons to the recognition tasks based on correlation indicator. Proc Inst Syst Program RAS (Proc ISP RAS) 33(1):33–46
Vershkov NN, Kuchukov VA, Kuchukova NN (2019) The theoretical approach to the search for a global extremum in the training of neural networks. Proc Inst Syst Program RAS 31(2):41–52
Kotelnikov VA (1956) The theory of potential noise immunity. Radio and Communication, St. Petersburg, USSR
Kharkevich AA (1972) Selected works. Information theory. Recognition of images. T.3. Science, Moscow, USSR
Ipatov V (2007) Broadband systems and code division of signals. Principles and applications. Technosphere, Moscow, Russia
LeCun Y (1998) The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/
Cook C (2012) Radar signals: an introduction to theory and application. Elsevier
Ahmed N, Rao KR (2012) Orthogonal transforms for digital signal processing. Springer, Heidelberg
Vorobiev VI, Gribunin VG (1999) Theory and practice of wavelet transform. Military University of Communications, Saint Petersburg, Russia
Sikarev AA, Lebedev ON (1983) Microelectronic devices for the formation and processing of complex signals. Radio and Communication, Moscow, USSR
Haar A (1910) On the theory of orthogonal systems of functions. Math Ann 69:331–371
Genchai R, Selcuk F, Whitcher B (2001) Introduction to wavelets and other filtering techniques in finance and economics. Academic Press, New York
Alexandridis AK, Zapranis AD (2013) Wavelet neural networks: a practical guide. Neural Netw 42:1–27
Cui Z, Chen W, Chen Y (2016) Multi-scale convolutional neural networks for time series classification. arXiv preprint arXiv:1603.06995
Acknowledgements
This work has been supported by the North-Caucasus Center for Mathematical Research subject to Agreement №. 075-02-2021-1749 with the Ministry of Science and Higher Education of the Russian Federation, while part of the study was funded by RFBR, Project Number 20-37-70023.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nikolay, V., Mikhail, B., Viktor, K., Natalia, K. (2022). Neural Network Analysis for Image Classification. In: Tchernykh, A., Alikhanov, A., Babenko, M., Samoylenko, I. (eds) Mathematics and its Applications in New Computer Systems. MANCS 2021. Lecture Notes in Networks and Systems, vol 424. Springer, Cham. https://doi.org/10.1007/978-3-030-97020-8_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-97020-8_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97019-2
Online ISBN: 978-3-030-97020-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)