Fuzzy Neural Networks that Change their Configuration.

Standard

Fuzzy Neural Networks that Change their Configuration. / Косовская, Татьяна Матвеевна.

In: Programming and Computer Software, Vol. 50, No. Suppl 1, 11.2024, p. S10-S17.

Research output: Contribution to journal › Article › peer-review

BibTeX

@article{dbfa392837b642b1891ca38b0b667ad9,

title = "Fuzzy Neural Networks that Change their Configuration.",

abstract = "Abstract: An analogue of a neural network, the number of layers and the number of cells in which may be changed during its retraining is suggested in the paper. The main instrument for constructing such a network is extraction of maximal common properties of pairs of objects in the training set and of that ones used for retraining. The degree of coincidence of a recognized object with the one presented in the training set may be calculated using their maximal common properties. Computational complexities of such a network construction, recognition process and the network retraining are proved. A brief description of a similar network proposed by the author earlier for complex structured objects described using predicate calculus is presented. The analysis of comparison of computational complexity of a complex structured object recognition with various methods of their description is given.",

keywords = "нейронная сеть, максимальное общее свойство объектов, степень совпадения, вычислительная сложность, computational complexity, degree of coincidence, maximal common property of objects, neural network",

author = "Косовская, {Татьяна Матвеевна}",

year = "2024",

month = nov,

doi = "10.1134/s036176882470035x",

language = "English",

volume = "50",

pages = "S10--S17",

journal = "Programming and Computer Software",

issn = "0361-7688",

publisher = "МАИК {"}Наука/Интерпериодика{"}",

number = "Suppl 1",

}

RIS

TY - JOUR

T1 - Fuzzy Neural Networks that Change their Configuration.

AU - Косовская, Татьяна Матвеевна

PY - 2024/11

Y1 - 2024/11

N2 - Abstract: An analogue of a neural network, the number of layers and the number of cells in which may be changed during its retraining is suggested in the paper. The main instrument for constructing such a network is extraction of maximal common properties of pairs of objects in the training set and of that ones used for retraining. The degree of coincidence of a recognized object with the one presented in the training set may be calculated using their maximal common properties. Computational complexities of such a network construction, recognition process and the network retraining are proved. A brief description of a similar network proposed by the author earlier for complex structured objects described using predicate calculus is presented. The analysis of comparison of computational complexity of a complex structured object recognition with various methods of their description is given.

AB - Abstract: An analogue of a neural network, the number of layers and the number of cells in which may be changed during its retraining is suggested in the paper. The main instrument for constructing such a network is extraction of maximal common properties of pairs of objects in the training set and of that ones used for retraining. The degree of coincidence of a recognized object with the one presented in the training set may be calculated using their maximal common properties. Computational complexities of such a network construction, recognition process and the network retraining are proved. A brief description of a similar network proposed by the author earlier for complex structured objects described using predicate calculus is presented. The analysis of comparison of computational complexity of a complex structured object recognition with various methods of their description is given.

KW - нейронная сеть

KW - максимальное общее свойство объектов

KW - степень совпадения

KW - вычислительная сложность

KW - computational complexity

KW - degree of coincidence

KW - maximal common property of objects

KW - neural network

UR - https://www.mendeley.com/catalogue/eff15abf-604b-39cb-aa50-7b00d75265ab/

U2 - 10.1134/s036176882470035x

DO - 10.1134/s036176882470035x

M3 - Article

VL - 50

SP - S10-S17

JO - Programming and Computer Software

JF - Programming and Computer Software

SN - 0361-7688

IS - Suppl 1

ER -

ID: 126658310