| DC Field | Value | Language |
|---|
| dc.contributor.author | Kotsovsky, Vladyslav | |
| dc.contributor.author | Geche, Fedir | |
| dc.contributor.author | Batyuk, Anatoliy | |
| dc.coverage.temporal | 21-25 August 2018, Lviv | |
| dc.date.accessioned | 2020-06-19T12:05:42Z | - |
| dc.date.available | 2020-06-19T12:05:42Z | - |
| dc.date.created | 2018-02-28 | |
| dc.date.issued | 2018-02-28 | |
| dc.identifier.citation | Kotsovsky V. Finite Generalization of the Offline Spectral Learning / Vladyslav Kotsovsky, Fedir Geche, Anatoliy Batyuk // Data stream mining and processing : proceedings of the IEEE second international conference, 21-25 August 2018, Lviv. — Львів : Lviv Politechnic Publishing House, 2018. — P. 356–360. — (Hybrid Systems of Computational Intelligence). | |
| dc.identifier.isbn | © Національний університет „Львівська політехніка“, 2018 | |
| dc.identifier.isbn | © Національний університет „Львівська політехніка“, 2018 | |
| dc.identifier.uri | https://ena.lpnu.ua/handle/ntb/52523 | - |
| dc.description.abstract | We study the problem of offline learning discrete
functions on polynomial threshold units over specified set of
polynomial. Our approach is based on the generalization of the
classical "Relaxation" method of solving linear inequalities.
We give theoretical reason justifying heuristic modification
improving the performance of spectral learning algorithm. We
demonstrate that if the normalizing factor satisfies sufficient
conditions, then the learning procedure is finite and stops after
some steps, producing the weight vector of the polynomial
threshold unit realizing the given threshold function. Our
approach can be applied in hybrid systems of computational
intelligence. | |
| dc.format.extent | 356-360 | |
| dc.language.iso | en | |
| dc.publisher | Lviv Politechnic Publishing House | |
| dc.relation.ispartof | Data stream mining and processing : proceedings of the IEEE second international conference, 2018 | |
| dc.subject | offline learning | |
| dc.subject | polynomial threshold unit | |
| dc.subject | threshold function | |
| dc.subject | artificial neural network | |
| dc.title | Finite Generalization of the Offline Spectral Learning | |
| dc.type | Conference Abstract | |
| dc.rights.holder | © Національний університет “Львівська політехніка”, 2018 | |
| dc.contributor.affiliation | Uzhhorod National University | |
| dc.contributor.affiliation | Lviv Polytechnic National University | |
| dc.format.pages | 5 | |
| dc.identifier.citationen | Kotsovsky V. Finite Generalization of the Offline Spectral Learning / Vladyslav Kotsovsky, Fedir Geche, Anatoliy Batyuk // Data stream mining and processing : proceedings of the IEEE second international conference, 21-25 August 2018, Lviv. — Lviv Politechnic Publishing House, 2018. — P. 356–360. — (Hybrid Systems of Computational Intelligence). | |
| dc.relation.references | [1] S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. Upper Saddle River, NJ: Prentice Hall, 1999. | |
| dc.relation.references | [2] T. Motzkin and I. Schoenberg, “The relaxation method for linear equalities,” Canadian Journal of Math., vol. 6, pp. 393−404, 1954. | |
| dc.relation.references | [3] R. Duda, P. Hart and D. Stork, Pattern Classification, 2nd ed. New York: Wiley-Interscience, 2001. | |
| dc.relation.references | [4] M. L. Dertouzos, Threshold Logic: A Synthesis Approach. Cambridge, MA: The MIT Press, 1965. | |
| dc.relation.references | [5] F. Geche. Analysis of Discrete Functions and Logical Circuits in Neural Basis. Uzhgorod: Vydavnytstvo V. Padyaka, 2010. (in Ukrainian) | |
| dc.relation.references | [6] S. Hampson and D. Kibler, “Minimum generalization via reflection: a fast linear threshold learner,” Machine Learning vol. 37(1), pp. 51-73, 1999. | |
| dc.relation.references | [7] J. Bruck, “Harmonic analysis of polynomial threshold functions,” Siam Journal on Discrete Mathematics, vol. 3 (2), pp. 168–177, 1990. | |
| dc.relation.references | [8] F. Е. Geche, V. M. Kotsovsky and A. Ye. Batyuk, “Learning algorithms for generalized neurons over character set,” Zbirnyk naukovykh prats instytutu problem modelyuvannya v energetytsi NAN Ukrayiny, vyp. 41, pp. 124-136, 2007. (in Ukrainian) | |
| dc.relation.references | [9] I. Tsmots, V. Teslyuk, T. Teslyuk and I. Ihnatyev, “Basic components of neuronetworks with parallel vertical group data real-time processing,” Advances in Intelligent Systems and Computing, vol. 689, Springer, Cham., pp. 558–576, 2018. | |
| dc.relation.references | [10]V. Teslyuk, V. Beregovskyi, P. Denysyuk, T. Teslyuk and A. Lozynskyi, “Development and implementation of the technical accident prevention subsystem for the smart home system,” International Journal of Intelligent Systems and Applications, vol. 10, No.1, pp. 1–8, 2018. | |
| dc.relation.references | [11]F. Geche, V. Kotsovsky and A. Batyuk, “Synthesis of the integer neural elements,” in Proceedings of the International Conference on Computer Sciences and Information Technologies CSIT 2015, Lviv, Ukraine, September 14-17 2015, pp. 121–136. | |
| dc.relation.referencesen | [1] S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. Upper Saddle River, NJ: Prentice Hall, 1999. | |
| dc.relation.referencesen | [2] T. Motzkin and I. Schoenberg, "The relaxation method for linear equalities," Canadian Journal of Math., vol. 6, pp. 393−404, 1954. | |
| dc.relation.referencesen | [3] R. Duda, P. Hart and D. Stork, Pattern Classification, 2nd ed. New York: Wiley-Interscience, 2001. | |
| dc.relation.referencesen | [4] M. L. Dertouzos, Threshold Logic: A Synthesis Approach. Cambridge, MA: The MIT Press, 1965. | |
| dc.relation.referencesen | [5] F. Geche. Analysis of Discrete Functions and Logical Circuits in Neural Basis. Uzhgorod: Vydavnytstvo V. Padyaka, 2010. (in Ukrainian) | |
| dc.relation.referencesen | [6] S. Hampson and D. Kibler, "Minimum generalization via reflection: a fast linear threshold learner," Machine Learning vol. 37(1), pp. 51-73, 1999. | |
| dc.relation.referencesen | [7] J. Bruck, "Harmonic analysis of polynomial threshold functions," Siam Journal on Discrete Mathematics, vol. 3 (2), pp. 168–177, 1990. | |
| dc.relation.referencesen | [8] F. E. Geche, V. M. Kotsovsky and A. Ye. Batyuk, "Learning algorithms for generalized neurons over character set," Zbirnyk naukovykh prats instytutu problem modelyuvannya v energetytsi NAN Ukrayiny, vyp. 41, pp. 124-136, 2007. (in Ukrainian) | |
| dc.relation.referencesen | [9] I. Tsmots, V. Teslyuk, T. Teslyuk and I. Ihnatyev, "Basic components of neuronetworks with parallel vertical group data real-time processing," Advances in Intelligent Systems and Computing, vol. 689, Springer, Cham., pp. 558–576, 2018. | |
| dc.relation.referencesen | [10]V. Teslyuk, V. Beregovskyi, P. Denysyuk, T. Teslyuk and A. Lozynskyi, "Development and implementation of the technical accident prevention subsystem for the smart home system," International Journal of Intelligent Systems and Applications, vol. 10, No.1, pp. 1–8, 2018. | |
| dc.relation.referencesen | [11]F. Geche, V. Kotsovsky and A. Batyuk, "Synthesis of the integer neural elements," in Proceedings of the International Conference on Computer Sciences and Information Technologies CSIT 2015, Lviv, Ukraine, September 14-17 2015, pp. 121–136. | |
| dc.citation.conference | IEEE second international conference "Data stream mining and processing" | |
| dc.citation.spage | 356 | |
| dc.citation.epage | 360 | |
| dc.coverage.placename | Львів | |
| Appears in Collections: | Data stream mining and processing : proceedings of the IEEE second international conference
|
