Principles of ontophylogenetic development of artificial general intelligence systems based on multi-agent neurocognitive architectures

The purpose of the study is to study the possibilities of multigenerational optimization of behavior control systems for agents of general artificial intelligence capable of independently solving a universal range of tasks in a real environment. The main principles of ontophylogenetic synthesis of c...

Full description

Bibliographic Details
Main Authors: Anchekov M.I., Apshev A.Z., Bzhikhatlov K.Ch., Kankulov S.A., Nagoev Z.V., Nagoeva O.V., Pshenokova I.A.
Format: Article
Language:English
Published: EDP Sciences 2024-01-01
Series:BIO Web of Conferences
Online Access:https://www.bio-conferences.org/articles/bioconf/pdf/2024/03/bioconf_aquaculture2024_02015.pdf
_version_ 1797353023311183872
author Anchekov M.I.
Apshev A.Z.
Bzhikhatlov K.Ch.
Kankulov S.A.
Nagoev Z.V.
Nagoeva O.V.
Pshenokova I.A.
author_facet Anchekov M.I.
Apshev A.Z.
Bzhikhatlov K.Ch.
Kankulov S.A.
Nagoev Z.V.
Nagoeva O.V.
Pshenokova I.A.
author_sort Anchekov M.I.
collection DOAJ
description The purpose of the study is to study the possibilities of multigenerational optimization of behavior control systems for agents of general artificial intelligence capable of independently solving a universal range of tasks in a real environment. The main principles of ontophylogenetic synthesis of control systems for agents of general artificial intelligence based on multi-agent neurocognitive architectures have been developed. Methods and algorithms for synthesizing the phenotypes of control systems of intelligent agents according to their genotypes are proposed. A software package for simulating the processes of ontophylogenetic synthesis of multi-agent neurocognitive architectures has been developed and experiments have been carried out to create phenotypes of intelligent agents based on them. A complex genome of an intelligent agent has been developed, the features of a multichromosome genetic algorithm for organizing calculations in the paradigm of multigenerational optimization of multiagent neurocognitive architectures have been established and substantiated. It is shown that multigenerational optimization of the multi-agent neurocognitive architecture of intelligent agents can contribute to the achievement of adaptive resistance to the operating conditions of a general artificial intelligence agent, provide the synthesis of its suboptimal structural and functional scheme, accelerate learning and algorithms for finding solutions to a universal range of problems solved by this agent in its ecological niche.
first_indexed 2024-03-08T13:24:14Z
format Article
id doaj.art-0e23ae127eee4070a73f54257396cf2b
institution Directory Open Access Journal
issn 2117-4458
language English
last_indexed 2024-03-08T13:24:14Z
publishDate 2024-01-01
publisher EDP Sciences
record_format Article
series BIO Web of Conferences
spelling doaj.art-0e23ae127eee4070a73f54257396cf2b2024-01-17T14:59:23ZengEDP SciencesBIO Web of Conferences2117-44582024-01-01840201510.1051/bioconf/20248402015bioconf_aquaculture2024_02015Principles of ontophylogenetic development of artificial general intelligence systems based on multi-agent neurocognitive architecturesAnchekov M.I.0Apshev A.Z.1Bzhikhatlov K.Ch.2Kankulov S.A.3Nagoev Z.V.4Nagoeva O.V.5Pshenokova I.A.6Kabardino-Balkarian Scientific Center of the Russian Academy of SciencesKabardino-Balkarian Scientific Center of the Russian Academy of SciencesKabardino-Balkarian Scientific Center of the Russian Academy of SciencesKabardino-Balkarian Scientific Center of the Russian Academy of SciencesKabardino-Balkarian Scientific Center of the Russian Academy of SciencesKabardino-Balkarian Scientific Center of the Russian Academy of SciencesKabardino-Balkarian Scientific Center of the Russian Academy of SciencesThe purpose of the study is to study the possibilities of multigenerational optimization of behavior control systems for agents of general artificial intelligence capable of independently solving a universal range of tasks in a real environment. The main principles of ontophylogenetic synthesis of control systems for agents of general artificial intelligence based on multi-agent neurocognitive architectures have been developed. Methods and algorithms for synthesizing the phenotypes of control systems of intelligent agents according to their genotypes are proposed. A software package for simulating the processes of ontophylogenetic synthesis of multi-agent neurocognitive architectures has been developed and experiments have been carried out to create phenotypes of intelligent agents based on them. A complex genome of an intelligent agent has been developed, the features of a multichromosome genetic algorithm for organizing calculations in the paradigm of multigenerational optimization of multiagent neurocognitive architectures have been established and substantiated. It is shown that multigenerational optimization of the multi-agent neurocognitive architecture of intelligent agents can contribute to the achievement of adaptive resistance to the operating conditions of a general artificial intelligence agent, provide the synthesis of its suboptimal structural and functional scheme, accelerate learning and algorithms for finding solutions to a universal range of problems solved by this agent in its ecological niche.https://www.bio-conferences.org/articles/bioconf/pdf/2024/03/bioconf_aquaculture2024_02015.pdf
spellingShingle Anchekov M.I.
Apshev A.Z.
Bzhikhatlov K.Ch.
Kankulov S.A.
Nagoev Z.V.
Nagoeva O.V.
Pshenokova I.A.
Principles of ontophylogenetic development of artificial general intelligence systems based on multi-agent neurocognitive architectures
BIO Web of Conferences
title Principles of ontophylogenetic development of artificial general intelligence systems based on multi-agent neurocognitive architectures
title_full Principles of ontophylogenetic development of artificial general intelligence systems based on multi-agent neurocognitive architectures
title_fullStr Principles of ontophylogenetic development of artificial general intelligence systems based on multi-agent neurocognitive architectures
title_full_unstemmed Principles of ontophylogenetic development of artificial general intelligence systems based on multi-agent neurocognitive architectures
title_short Principles of ontophylogenetic development of artificial general intelligence systems based on multi-agent neurocognitive architectures
title_sort principles of ontophylogenetic development of artificial general intelligence systems based on multi agent neurocognitive architectures
url https://www.bio-conferences.org/articles/bioconf/pdf/2024/03/bioconf_aquaculture2024_02015.pdf
work_keys_str_mv AT anchekovmi principlesofontophylogeneticdevelopmentofartificialgeneralintelligencesystemsbasedonmultiagentneurocognitivearchitectures
AT apshevaz principlesofontophylogeneticdevelopmentofartificialgeneralintelligencesystemsbasedonmultiagentneurocognitivearchitectures
AT bzhikhatlovkch principlesofontophylogeneticdevelopmentofartificialgeneralintelligencesystemsbasedonmultiagentneurocognitivearchitectures
AT kankulovsa principlesofontophylogeneticdevelopmentofartificialgeneralintelligencesystemsbasedonmultiagentneurocognitivearchitectures
AT nagoevzv principlesofontophylogeneticdevelopmentofartificialgeneralintelligencesystemsbasedonmultiagentneurocognitivearchitectures
AT nagoevaov principlesofontophylogeneticdevelopmentofartificialgeneralintelligencesystemsbasedonmultiagentneurocognitivearchitectures
AT pshenokovaia principlesofontophylogeneticdevelopmentofartificialgeneralintelligencesystemsbasedonmultiagentneurocognitivearchitectures