Recognition of Generalized Patterns by a Differential Polynomial Neural Network
Abstract
A lot of problems involve unknown data relations, identification of which can serve as a generalization of their qualities. Relative values of variables are applied in this case, and not the absolute values, which can better make use of data properties in a wide range of the validity. This resembles more to the functionality of the brain, which seems to generalize relations of variables too, than a common pattern classification. Differential polynomial neural network is a new type of neural network designed by the author, which constructs and approximates an unknown differential equation of dependent variables using special type of root multi-parametric polynomials. It creates fractional partial differential terms, describing mutual derivative changes of some variables, likewise the differential equation does. Particular polynomials catch relations of given combinations of input variables. This type of identification is not based on a whole-pattern similarity, but only to the learned hidden generalized relations of variables.
Keywords:
polynomial neural network, dependence of variables identification, differential equation approximation, rational integral functionDownloads
References
L. Benuskova, Neuron and brain. Cognitive sciences, Calligram Bratislava, 2002 (in Slovak)
A. G. Ivakhnenko, “Polynomial theory of complex systems”, IEEE Transactions on systems, Vol. SMC-1, No. 4, pp. 364-378, 1971 DOI: https://doi.org/10.1109/TSMC.1971.4308320
J. Hronec, Differential equations II., SAV Bratislava, 1958 (in Slovak)
R. Rychnovsky, J. Vyborna, Partial differential equations and some of their solutions, Publ. SNTL Praha, 1970 (in Czech)
J. Kunes, O. Vavroch, V. Franta, Principles of modelling, SNTL Praha, 1989 (in Czech)
I. Kluvanek, L. Misík, M. Svec, Matematics I., II., SNTL Bratislava, 1966 (in Slovak)
S. Das, A. Abraham, A. Konar, “Particle swarm ptimization and differential evolution algorithms: Technical snalysis, applications and hybridization perspectives”, Computer and Information Science, Vol. 38, pp. 1-38, 2008. DOI: https://doi.org/10.1007/978-3-540-78297-1_1
B. B. Misra, S. Dehuri, P.K. Dash, G. Panda, “A reduced and comprehensible polynomial neural network for classification”, Pattern recognition letters, Vol. 29, No. 12, pp. 1705-1715, 2008.
L. Zjavka, “Generalization of patterns by identification with polynomial neural network”, Journal of Electrical Engineering, Vol. 61, No. 2, pp. 120-124, 2010 DOI: https://doi.org/10.2478/v10187-010-0017-4
L. Zjavka, “Construction and adjustment of differential polynomial neural network”, Journal of Engineering and Computer Innovations, Vol. 2, No. 3, pp. 40-50, 2011
Downloads
How to Cite
License
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
