Abstract
The paper deals with the issues concerning the application of bithreshold-like neural units in the solving of the classification tasks. The fully connected 2-layer feedforward network architecture with the hidden layer consisting of bithreshold neurons is considered in the paper. We design the neural network multicategory classifier based on such an architecture. The upper bound is given on the size of the bithreshold network, which is capable to recognize an arbitrary partition of the given finite set of patterns into a predefined number of classes. The synthesis algorithm is proposed for such neural networks. We also introduce the model of centered bithreshold neuron whose two boundary surfaces get closer as far as the distance to the center of the neuron increases, which is often more convenient in the design of multicategory classifiers. The synthesis algorithm is described for neural network classifier whose hidden layer consists of centered bithreshold neurons. For both type of networks, we give simulation results of the classifier performance on the real data sets and discuss the influence of algorithm parameters on the process of synthesis, quality of the network performance and the representational capacity of classifier.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Izonin, I., Kryvinska, N., Tkachenko, R., Zub, K., Vitynskyi, P.: An extended-input GRNN and its application. In: Shakshuki, E., Yasar, A., Malik, H. (eds.) Procedia Computer Science, vol. 160, pp. 578–583. Elsevier B.V. (2019). https://doi.org/10.1016/j.procs.2019.11.044
Geche, F., Kotsovsky, V., Batyuk, A., Geche, S., Vashkeba, M.: Synthesis of time series forecasting scheme based on forecasting models system. CEUR Workshop Proc. 1356, 121–136 (2015)
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.) CSIT 2017. AISC, vol. 689, pp. 538–557. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-70581-1_38
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.O. (eds.) CSIT 2018. AISC, 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.: Bithreshold neural network classifier. In: 2020 IEEE 15th International Conference on Computer Sciences and Information Technologies, CSIT 2020, in press (2020)
Lupei, M., Mitsa, A., Repariuk, V., Sharkan, V.: Identication of authorship of Ukrainian-language texts of journalistic style using neural networks. Eastern-Euro. J. Enerprise Technol. 1(2(103)), 30–36 (2020). https://doi.org/10.15587/1729-4061.2020.195041
Mukalov, P., Zelinskyi, O., Levkovych, R., Tarnavskyi, P., Pylypm, A., Shakhovska, N.: Development of system for auto-tagging articles, based on neural network. CEUR Workshop Proc. 2362, 106–115 (2019)
Kazarian, A., Teslyuk, V.: Optimization of neural network structure for smart house systems. In: 2019 IEEE 2nd Ukraine Conference on Electrical and Computer Engineering, (UKRCON), pp. 562–565 (2019). https://doi.org/10.1109/UKRCON.2019.8879772
Tsmots, I., Tsymbal, Y., Skorokhoda, O., Tkachenko, R.: Neural-like methods and hardware structures for real-time data encryption and decryption. In: 2019 IEEE 14th International Conference on Computer Sciences and Information Technologies, CSIT 2019, pp. 248–253. Lviv (2019). https://doi.org/10.1109/STC-CSIT.2019.8929809
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. In Shakshuki, E., Yasar, A., Malik, H. (eds.) Procedia Computer Science, vol. 160, pp. 521–526. Elsevier B.V. (2019). https://doi.org/10.1016/j.procs.2019.11.054
Tkachenko, R., Izonin, I., Kryvinska, N., Dronyuk, I., Zub, K.: An approach towards increasing prediction accuracy for the recovery of missing IoT data based on the GRNN-SGTM ensemble. Sensors, 20(9), 2625 (2020). https://doi.org/10.3390/s20092625
Haykin, S.: Neural Networks and Learning Machines, 3rd edn. Pearson Education, Upper Saddle River (2009)
Anthony, M.: Discrete Mathematics of Neural Networks: Selected Topics. SIAM, Philadelphia (2001)
Haring, D.: Multiple threshold perceptron. Pattern Recognition EC-15, 45–65 (1965)
Kotsovsky, V., Geche, F., Batyuk, A.: On the computational complexity of learning bithreshold neural units and networks. In: Lytvynenko, V., Babichev, S., Wójcik, W., Vynokurova, O., Vyshemyrskaya, S., Radetskaya, S. (eds.) ISDMCI 2019. AISC, vol. 1020, pp. 189–202. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-26474-1_14
Takiyama, R.: The separating capacity of multithreshold threshold element. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-7(1), 112–116 (1985)
Olafsson, S., Abu-Mostafa, Y.S.: The capacity of multilevel threshold function. IEEE Trans. Pattern Anal. Mach. Intell. 10(2), 277–281 (1988)
Kotsovsky, V., Batyuk, A., Mykoriak, I.: The computation power and capacity of bithreshold neurons. In: 2020 IEEE 15th International Conference on Computer Sciences and Information Technologies, CSIT 2020, in press (2020)
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.) ICCSEEA 2018. AISC, vol. 754, pp. 578–587. Springer, Cham (2019). https://doi.org/10.1007/978-3-319-91008-6_58
Tsmots, I., Teslyuk, V., Teslyuk, T., Ihnatyev, I.: Basic components of neuronetworks with parallel vertical group data real-time processing. In: Shakhovska, N., Stepashko, V. (eds.) CSIT 2017. AISC, vol. 689, pp. 558–576. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-70581-1_39
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, pp. 57–59. Lviv (2015)
Polishchuk, V.: Fuzzy method for evaluating commercial projects of different origin. J. Autom. Inf. Sci. 50(5), 60–73 (2018). https://doi.org/10.1615/JAutomatInfScien.v50.i5.60
Baum, E.B.: On the capabilities of multilayer perceptrons. J. Complexity 4(3), 193–215 (1988). https://doi.org/10.1016/0885-064X(88)90020-9
Deolalikar, V.: A two-layer paradigm capable of forming arbitrary decision regions in input space. IEEE Trans. Neural Netw. 13(1), 15–21 (2002)
Kotsovsky, V., Batyuk, A.: Representational capabilities and learning of bithreshold neural networks. In: Babichev, S., Lytvynenko, V., Wójcik, W., Vyshemyrskaya, S. (eds.) ISDMCI 2020. AISC, vol. 1246, pp. 499–514. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-54215-3_32
Geche, F., Kotsovsky, V., Batyuk, A.: Synthesis of the integer neural elements. In: 10th International Conference on Computer Sciences and Information Technologies, CSIT 2015, pp. 63–66. Lviv (2015). https://doi.org/10.1109/STC-CSIT.2015.7325432
Dua, D., Graff, C.: UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. University of California, School of Information and Computer Science, Irvine, CA (2019)
Polishchuk, V.: Technology to improve the safety of choosing alter-natives by groups of goals. J. Autom. Inf. Sci. 51(9), 66–76 (2019). https://doi.org/10.1615/JAutomatInfScien.v51.i9.60
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, pp. 356–360. Lviv (2018). https://doi.org/10.1109/DSMP.2018.8478584
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kotsovsky, V., Geche, F., Batyuk, A. (2021). Synthesis of the Centered Bithreshold Neural Network Classifier. In: Shakhovska, N., Medykovskyy, M.O. (eds) Advances in Intelligent Systems and Computing V. CSIT 2020. Advances in Intelligent Systems and Computing, vol 1293. Springer, Cham. https://doi.org/10.1007/978-3-030-63270-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-63270-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63269-4
Online ISBN: 978-3-030-63270-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)