Standard

Self-modificated predicate networks. / Kosovskaya, T.

In: International Journal on Information Theory and Applications, Vol. 22, No. 3, 2015, p. 245–257.

Research output: Contribution to journal › Article

Harvard

Kosovskaya, T 2015, 'Self-modificated predicate networks', International Journal on Information Theory and Applications, vol. 22, no. 3, pp. 245–257.

APA

Kosovskaya, T. (2015). Self-modificated predicate networks. International Journal on Information Theory and Applications, 22(3), 245–257.

Vancouver

Kosovskaya T. Self-modificated predicate networks. International Journal on Information Theory and Applications. 2015;22(3):245–257.

Author

Kosovskaya, T. / Self-modificated predicate networks. In: International Journal on Information Theory and Applications. 2015 ; Vol. 22, No. 3. pp. 245–257.

BibTeX

@article{1c33a170e79d4497b350675443630737,
title = "Self-modificated predicate networks",
abstract = "A model of self-modificated predicate network with cells implementing predicate formulas in the form of elementary conjunction is suggested. Unlike a classical neuron network the proposed model has two blocks: a training block and a recognition block. If a recognition block has a mistake then the control is transferred to a training block. Always after a training block run the configuration of a recognition block is changed. The base of the proposed predicate network is logic-objective approach to AI problems solving and level description of classes.",
keywords = "artificial intelligence, pattern recognition, predicate calculus, level description of a class.",
author = "T. Kosovskaya",
year = "2015",
language = "English",
volume = "22",
pages = "245–257",
journal = "International Journal on Information Theory and Applications",
issn = "1310-0513",
number = "3",

}

RIS

TY - JOUR

T1 - Self-modificated predicate networks

AU - Kosovskaya, T.

PY - 2015

Y1 - 2015

N2 - A model of self-modificated predicate network with cells implementing predicate formulas in the form of elementary conjunction is suggested. Unlike a classical neuron network the proposed model has two blocks: a training block and a recognition block. If a recognition block has a mistake then the control is transferred to a training block. Always after a training block run the configuration of a recognition block is changed. The base of the proposed predicate network is logic-objective approach to AI problems solving and level description of classes.

AB - A model of self-modificated predicate network with cells implementing predicate formulas in the form of elementary conjunction is suggested. Unlike a classical neuron network the proposed model has two blocks: a training block and a recognition block. If a recognition block has a mistake then the control is transferred to a training block. Always after a training block run the configuration of a recognition block is changed. The base of the proposed predicate network is logic-objective approach to AI problems solving and level description of classes.

KW - artificial intelligence

KW - pattern recognition

KW - predicate calculus

KW - level description of a class.

UR - http://www.foibg.com/ijita/vol22/ijita22-03-p03.pdf

M3 - Article

VL - 22

SP - 245

EP - 257

JO - International Journal on Information Theory and Applications

JF - International Journal on Information Theory and Applications

SN - 1310-0513

IS - 3

ER -

ID: 101749160