Abstract
The paper deals with questions related to the ability of real-weighted bithreshold neurons and neural networks to solve the classification tasks. We study how many partitions of a finite set in n-dimensional vector space can be computed by using bithreshold neurons. The upper and lower bounds on the number of bithreshold dichotomies are proved. Our main theoretical result states that there exists \(\mathrm {\Theta }\left( m^{n+1}\right) \) bithreshold dichotomies of the set of m points in general position in n-dimensional space. We also estimate the Vapnik-Chervonenkis dimension of the class of bithreshold neurons. The problem of the synthesis of 2-layer bithreshold neural network for binary classification is considered. We demonstrate that an arbitrary dichotomy of m points in general position in n-dimensional space can be realized by 2-layer neural network containing at most \(\left\lceil m/(2n)\right\rceil \) bithreshold neurons in hidden layer and a single output threshold neuron. The learning algorithm with computational complexity \(O\left( m{{n}^{2}}+{{m}^{2}} \right) \) is proposed for such networks. We give simulation results of the network performance on real data sets and discuss the influence of algorithm parameters on the quality of learning and the representational capabilities of bithreshold networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anthony, M.: Discrete Mathematics of Neural Networks: Selected Topics. SIAM, Philadelphia (2001). https://doi.org/10.1137/1.9780898718539
Babichev, S., Taif, M.A., Lytvynenko, V.: Inductive model of data clustering based on the agglomerative hierarchical algorithm. In: Proceedings of the 2016 IEEE 1st International Conference on Data Stream Mining and Processing, pp. 19–22 (2016)
Baum, E.B.: On the capabilities of multilayer perceptrons. J. Complex. 4(3), 193–215 (1988). https://doi.org/10.1016/0885-064X(88)90020-9
Blum, A., Rives, R.: Training a 3-node neural network is NP-complete. Neural Netw. 5(1), 117–127 (1992). https://doi.org/10.1016/S0893-6080(05)80010-3
Cover, T.: Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE Trans. Electron. Comput. EC–14, 326–334 (1965)
Deolalikar, V.: A two-layer paradigm capable of forming arbitrary decision regions in input space. IEEE Trans. Neural Netw. 13(1), 15–21 (2002). https://doi.org/10.1109/72.977261
Geche, F., Kotsovsky, V., Batyuk, A.: Synthesis of the integer neural elements. In: 10th International Conference on Computer Sciences and Information Technologies, CSIT 2015, Lviv, pp. 63–66 (2015). https://doi.org/10.1109/STC-CSIT.2015.7325432
Geche, F., Kotsovsky, V., Batyuk, A., Geche, S., Vashkeba, M.: Synthesis of time series forecasting scheme based on forecasting models system. In: CEUR Workshop Proceedings, vol. 1356, pp. 121–136 (2015)
Géron, A.: Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, 2nd edn. O’Reilly Media Inc., Sebastopol (2019)
Haring, D.: Multiple threshold perceptron. IEEE Trans. Electron. Comput. EC–15, 45–65 (1965)
Izonin, I., Kryvinska, N., Tkachenko, R., Zub, K., Vitynskyi, P.: An extended-input GRNN and its application. Procedia Comput. Sci. 160, 578–583 (2019)
Izonin, I., Tkachenko, R., Kryvinska, N., Zub, K., Mishchuk, O., Lisovych, T.: Recovery of incomplete IoT sensed data using high-performance extended-input neural-like structure. Procedia Comput. Sci. 160, 521–526 (2019). https://doi.org/10.1016/j.procs.2019.11.054
Kazarian, A., Teslyuk, V., Tsmots, I., Tykhan, M.: Implementation of the face recognition module for the “smart” home using remote server. In: Shakhovska, N., Medykovskyy, M. (eds.) Advances in Intelligent Systems and Computing III. CSIT 2018. Advances in Intelligent Systems and Computing, vol. 871, pp. 17–27. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-01069-0_2
Kotsovsky, V., Geche, F., Batyuk, A.: Artificial complex neurons with half-plane-like and angle-like activation function. In: 10th International Conference on Computer Sciences and Information Technologies, CSIT 2015, Lviv, pp. 57–59 (2015). https://doi.org/10.1109/STC-CSIT.2015.7325430
Kotsovsky, V., Geche, F., Batyuk, A.: Finite generalization of the offline spectral learning. In: 2018 IEEE 2nd International Conference on Data Stream Mining and Processing, DSMP 2018, Lviv, pp. 356–360 (2018). https://doi.org/10.1109/DSMP.2018.8478584
Kotsovsky, V., Geche, F., Batyuk, A.: On the computational complexity of learning bithreshold neural units and networks. In: Lytvynenko, V., et al. (eds.) Lecture Notes in Computational Intelligence and Decision Making. ISDMCI 2019. Advances in Intelligent Systems and Computing, vol. 1020, pp. 189–202. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-26474-1_14
Lupei, M., Mitsa, A., Repariuk, V., Sharkan, V.: Identification of authorship of Ukrainian-language texts of journalistic style using neural networks. East.-Eur. J. Enterp. Technol. 1(2(103)), 30–36 (2020). https://doi.org/10.15587/1729-4061.2020.195041
Okrenets, S., Fefelov, A., Lytvynenko, V., Osypenko, V., Korobchynskyi, M., Voronenko, M.: Synthesis and learning of fuzzy neural networks for solving forecasting problems. In: 2017 IEEE 9th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, IDAACS 2017, vol. 2, pp. 1088–1093 (2017). https://doi.org/10.1109/IDAACS.2017.8095253
Olafsson, S., Abu-Mostafa, Y.S.: The capacity of multilevel threshold function. IEEE Trans. Pattern Anal. Mach. Intell. 10(2), 277–281 (1988)
Polishchuk, V.: Technology to improve the safety of choosing alternatives by groups of goals. J. Autom. Inf. Sci. 51(9), 66–76 (2019). https://doi.org/10.1615/JAutomatInfScien.v51.i9.60
Takiyama, R.: The separating capacity of multithreshold threshold element. IEEE Trans. Pattern Anal. Mach. Intell. PAMI–7(1), 112–116 (1985)
Teslyuk, T., Tsmots, I., Teslyuk, V., Medykovskyy, M., Opotyak, Y.: Architecture and models for system-level computer-aided design of the management system of energy efficiency of technological processes at the enterprise. In: Shakhovska, N., Stepashko, V. (eds.) Advances in Intelligent Systems and Computing II. CSIT 2017. Advances in Intelligent Systems and Computing, vol. 689, pp. 538–557. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-70581-1_38
Tkachenko, R., Izonin, I.: Model and principles for the implementation of neural-like structures based on geometric data transformations. In: Hu, Z., Petoukhov, S., Dychka, I., He, M. (eds.) Advances in Intelligent Systems and Computing, vol. 754, pp. 578–587. Springer, Cham (2019)
Tsmots, I., Skorokhoda, O., Tesliuk, T., Rabyk, V.: Designing features of hardware and software tools for intelligent processing of intensive data streams. In: 2016 IEEE 1st International Conference on Data Stream Mining and Processing, DSMP 2016, Lviv, pp. 332–335 (2016)
Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)
Vynokurova, O., Peleshko, D., Borzov, Y., Oskerko, S., Voloshyn, V.: Hybrid multidimensional wavelet-neuro-system and its learning using cross entropy cost function in pattern recognition. In: 2018 IEEE 2nd International Conference on Data Stream Mining and Processing, DSMP 2018, Lviv, pp. 305–309 (2018). https://doi.org/10.1109/DSMP.2018.8478608
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kotsovsky, V., Batyuk, A. (2021). Representational Capabilities and Learning of Bithreshold Neural Networks. In: Babichev, S., Lytvynenko, V., Wójcik, W., Vyshemyrskaya, S. (eds) Lecture Notes in Computational Intelligence and Decision Making. ISDMCI 2020. Advances in Intelligent Systems and Computing, vol 1246. Springer, Cham. https://doi.org/10.1007/978-3-030-54215-3_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-54215-3_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-54214-6
Online ISBN: 978-3-030-54215-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)