|
This article is cited in 3 scientific papers (total in 3 papers)
Theoretical and Applied Mathematics
Self-training Network with the Sells Implementing Predicate Formulas
T. M. Kosovskayaab a Saint Petersburg State University
b St. Petersburg Institute for Informatics and Automation of Russian Academy of Scientists (SPIIRAS)
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 transfered to a training block. Always after a training block implementation the configuration of a recognition block is changed. The base of the proposed logic-predicate network is a logic-objective approach to AI problems solving and level description of classes as well as the notion of partial deducibility which allows to extract common sub-formulas of elementary conjunctions
Keywords:
artificial intelligence, pattern recognition, predicate calculus formulas, level description of a class, self-training recognition network.
Citation:
T. M. Kosovskaya, “Self-training Network with the Sells Implementing Predicate Formulas”, Tr. SPIIRAN, 43 (2015), 94–113
Linking options:
https://www.mathnet.ru/eng/trspy842 https://www.mathnet.ru/eng/trspy/v43/p94
|
Statistics & downloads: |
Abstract page: | 162 | Full-text PDF : | 71 | First page: | 1 |
|