Geodesic
Universal expert system based on ontoepisosociophylogenetic training of federations of intelligent neurocognitive agents
News of the Kabardin-Balkar scientific center of RAS, Tome 26 (2024) no. 6, pp. 197-207.

Voir la notice de l'article provenant de la source Math-Net.Ru

The work is devoted to solve a scientific problem of developing a conceptual justification for the possibility of autonomous training of intelligent expert systems based on ontoepisociophylogenetic training of neurocognitive agents. The aim of the study is to develop basic principles of creating universal expert systems based on ontoepisociophylogenetic training of federated intelligent neurocognitive agents. The basic principles of ontoepisociophylogenetic training of universal federated expert systems have been developed. It is shown that the functional specialization of intelligent agents within a federation, subject to their cooperation in order to maximize the combined increment of the values of the target functions, allows overcoming efficiency limitations. The use of epigenetic algorithms for fixing ontological knowledge of intelligent agents within a federation in generations of evolutionary optimization is substantiated. The possibility of constructing multi-generational populations in order to increase the overall efficiency of a universal expert federated system is substantiated.
Keywords: artificial intelligence, multi-agent systems, neurocognitive architectures, ontoepisociophylogenetic algorithms, machine learning, universal expert systems 
@article{IZKAB_2024_26_6_a16,
     author = {Z. V. Nagoev and M. I. Anchekov and Zh. H. Kurashev and O. V. Nagoeva and I. A. Pshenokova and A. A. Khamov},
     title = {Universal expert system based on ontoepisosociophylogenetic training of federations of intelligent neurocognitive agents},
     journal = {News of the Kabardin-Balkar scientific center of RAS},
     pages = {197--207},
     publisher = {mathdoc},
     volume = {26},
     number = {6},
     year = {2024},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/IZKAB_2024_26_6_a16/}
}
TY  - JOUR
AU  - Z. V. Nagoev
AU  - M. I. Anchekov
AU  - Zh. H. Kurashev
AU  - O. V. Nagoeva
AU  - I. A. Pshenokova
AU  - A. A. Khamov
TI  - Universal expert system based on ontoepisosociophylogenetic training of federations of intelligent neurocognitive agents
JO  - News of the Kabardin-Balkar scientific center of RAS
PY  - 2024
SP  - 197
EP  - 207
VL  - 26
IS  - 6
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/IZKAB_2024_26_6_a16/
LA  - ru
ID  - IZKAB_2024_26_6_a16
ER  - 
%0 Journal Article
%A Z. V. Nagoev
%A M. I. Anchekov
%A Zh. H. Kurashev
%A O. V. Nagoeva
%A I. A. Pshenokova
%A A. A. Khamov
%T Universal expert system based on ontoepisosociophylogenetic training of federations of intelligent neurocognitive agents
%J News of the Kabardin-Balkar scientific center of RAS
%D 2024
%P 197-207
%V 26
%N 6
%I mathdoc
%U http://geodesic.mathdoc.fr/item/IZKAB_2024_26_6_a16/
%G ru
%F IZKAB_2024_26_6_a16
Z. V. Nagoev; M. I. Anchekov; Zh. H. Kurashev; O. V. Nagoeva; I. A. Pshenokova; A. A. Khamov. Universal expert system based on ontoepisosociophylogenetic training of federations of intelligent neurocognitive agents. News of the Kabardin-Balkar scientific center of RAS, Tome 26 (2024) no. 6, pp. 197-207. http://geodesic.mathdoc.fr/item/IZKAB_2024_26_6_a16/

[1] Z. V. Nagoev, M. I. Anchekov, K. Ch. Bzhikhatlov et al., “Ontoepisociophylogenetic development of general artificial intelligence systems based on multi agent neurocognitive architectures”, News of the Kabardino-Balkarian Scientific Center of RAS, 2022, no. 6 (110), 61–75 (In Russian)

[2] Z. V. Nagoev, M. I. Anchekov, A. Z. Apshev et al., “Formal model of the genome of an agent of general artificial intelligence based on multi-agent neurocognitive architectures”, News of the Kabardino-Balkarian Scientific Center of RAS, 2023, no. 5 (115), 11–24 (In Russian)

[3] Z. V. Nagoev, Intellectics or Thinking in Living and Artificial Systems, Izdatel'stvo KBNTS RAN, Nalchik:, 2013, 235 pp. (In Russian)

[4] Z. V. Nagoev, K. Ch. Bzhikhatlov, O. Z. Zagazezheva, “Neurocognitive methods and algorithms for federated learning of intelligent integrated information and control systems in a real communication environment”, Bulletin of the Southern Federal University. Engineering Sciences, 2024, no. 1 (237), 111–121 (In Russian)

[5] Z. V. Nagoev, O. V. Nagoeva, Symbol Grounding and Multi-Agent Neurocognitive Models of Natural Language Semantics, Izdatel'stvo KBNTS RAN, Nalchik:, 2022, 150 pp. (In Russian)

[6] M. A. Abazokov, M. I. Anchekov, K. Ch. Bzhikhatlov et al., “Analysis of the computational complexity of federated algorithms for neurocognitive control of simulation phenogenetic models of plants (metadata)”, News of the Kabardino-Balkarian Scientific Center of RAS, 2024, no. 5 (121), 107–129 (In Russian)