MODIFICATION OF A GEOMETRICAL ALGORITHM OF CHARACTERIZATIONk-VALUED THRESHOLD FUNCTIONS
( Pp. 132-139)

More about authors
Burdeliov Alexander Vladimirovich st. prepodavatel kafedry matematicheskogo modelirovaniya i analiza dannyh fakulteta prikladnoy matematiki i informatiki
Belarusian State University
For read the full article, please, register or log in
Abstract:
The article provides an overview of the known approaches to the characterization (learning) k-valued threshold functions. Proposed a new algorithm characterization of k-valued threshold functions, which based on a known geometrical algorithm. For this new algorithm proved it's convergence. Also we give the results of experimental comparisons between new algorithm and a known geometrical algorithm of characterization and Obradovic learning algorithm.
How to Cite:
Burdeliov A.V., (2018), MODIFICATION OF A GEOMETRICAL ALGORITHM OF CHARACTERIZATIONK-VALUED THRESHOLD FUNCTIONS. Computational Nanotechnology, 1: 132-139.
Reference list:
Belyakov-Bodin V.I., Rozenblit S.I. Issledovanie nekotorykh voprosov sinteza porogovykh funktsiy. M.: Institut teoreticheskoy i eksperimental noy fiziki Gos. Komiteta po ispol zovaniyu atomnoy energii SSSR, 1972.
Burdelyev A.V. O skhodimosti algoritma kharakterizatsii k-znachnykh porogovykh funktsiy // Prikladnaya diskretnaya matematika. Stat ya prinyata k pechati.
Burdelyev A.V., Nikonov V.G. O novom algoritme kharakterizatsii k-znachnykh porogovykh funktsiy // Computational nanotechnology. Vyp. № 1 // 2017, s. 7-14.
Burdelyev A.V., Nikonov V.G. O postroenii analiticheskogo zadaniya k-znachnoy porogovoy funktsii // Computational nanotechnology. Vyp. № 2 / 2015.
Butakov E.A. Metody sinteza releynykh ustroystv iz porogovykh elementov. M.: Energiya, 1970.
Dertouzos M. Porogovaya logika. M.: Mir, 1967.
Zolotykh N.YU. Rasshifrovka porogovykh i blizkikh k nim funktsiy. Dissert. dokt. fiz.-mat. nauk. FGBUN Institut matematiki im. S.L. Soboleva SO RAN. M., 2013.
Nikonov V.G. Osobennosti porogovykh predstavleniy k-znachnykh funktsiy // Trudy po diskretnoy matematike. 2008. T. 11. S. 60-85.
Minskiy M., Papert S. Perseptrony. M.: Mir, 1971.
Anthony M. Learning Multivalued Multithreshold Functions. CDAM Research Report LSE-CDAM-2003-03, January 2003.
Moraga C. Multiple-valued threshold logic. In: Optical Computing. Digital and Symbolic (R. Arrathoon, Ed.), 161-183.
Marcel Dekker Inc., N.Y., 1989. Ngom A., Synthesis of Multiple-Valued Logic Functions by Neural Networks, Ph.D. Thesis Dissertation, Computer Science Department, University of Ottawa, Ontario, October 1998.
Obradovic . Learning with Discrete Multi-Valued Neurons, Machine Learning // Proc. 7th Int l. Conf., 1990 / ed. B.W. Porter and R.J. Mooney. Austin, TX, Morgan-Kaufmann. Rp. 392-399.
Keywords:
threshold function, k-valued logic, geometric algorithm the characterization of threshold functions, the proof of convergence.