Structure of associative heterarchical memory

Objectives. Since the 20th century, artificial intelligence methods can be divided into two paradigms: top-down and bottom-up. While the methods of the ascending paradigm are difficult to interpret as natural language outputs, those applied according to the descending paradigm make it difficult to a...

Full description

Saved in:
Bibliographic Details
Main Authors: R. V. Dushkin, V. A. Lelekova, V. Y. Stepankov, S. Fadeeva
Format: Article
Language:Russian
Published: MIREA - Russian Technological University 2022-10-01
Series:Российский технологический журнал
Subjects:
Online Access:https://www.rtj-mirea.ru/jour/article/view/563
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850048777769975808
author R. V. Dushkin
V. A. Lelekova
V. Y. Stepankov
S. Fadeeva
author_facet R. V. Dushkin
V. A. Lelekova
V. Y. Stepankov
S. Fadeeva
author_sort R. V. Dushkin
collection DOAJ
description Objectives. Since the 20th century, artificial intelligence methods can be divided into two paradigms: top-down and bottom-up. While the methods of the ascending paradigm are difficult to interpret as natural language outputs, those applied according to the descending paradigm make it difficult to actualize information. Thus, natural language processing (NLP) by artificial intelligence remains a pressing problem of our time. The main task of NLP is to create applications that can process and understand natural languages. According to the presented approach to the construction of artificial intelligence agents (AI-agents), processing of natural language should be conducted at two levels: at the bottom, methods of the ascending paradigm are employed, while symbolic methods associated with the descending paradigm are used at the top. To solve these problems, the authors of the present paper propose a new mathematical formalism: associative heterarchical memory (AH-memory), whose structure and functionality are based both on bionic principles and on the achievements of top-down and bottom-up artificial intelligence paradigms.Methods. Natural language recognition algorithms were used in conjunction with various artificial intelligence methods.Results. The problem of character binding as applied to AH-memory was explored by the research group in earlier research. Here, abstract symbol binding was performed using multi-serial integration, eventually converting the primary symbols produced by the program into integrated abstract symbols. The present paper provides a comprehensive description of AH-memory in the form of formulas, along with their explanations and corresponding schemes.Conclusions. The most universal structure of AH-memory is presented. When working with AH-memory, a developer should select from a variety of possible module sets those AH-memory components that support the most successful and efficient functioning of the AI-agent.
format Article
id doaj-art-d1d770a19ff94151901fe3098fe1b073
institution DOAJ
issn 2782-3210
2500-316X
language Russian
publishDate 2022-10-01
publisher MIREA - Russian Technological University
record_format Article
series Российский технологический журнал
spelling doaj-art-d1d770a19ff94151901fe3098fe1b0732025-08-20T02:53:53ZrusMIREA - Russian Technological UniversityРоссийский технологический журнал2782-32102500-316X2022-10-0110571510.32362/2500-316X-2022-10-5-7-15336Structure of associative heterarchical memoryR. V. Dushkin0V. A. Lelekova1V. Y. Stepankov2S. Fadeeva3Artificial Intelligence AgencyArtificial Intelligence AgencyArtificial Intelligence AgencyArtificial Intelligence AgencyObjectives. Since the 20th century, artificial intelligence methods can be divided into two paradigms: top-down and bottom-up. While the methods of the ascending paradigm are difficult to interpret as natural language outputs, those applied according to the descending paradigm make it difficult to actualize information. Thus, natural language processing (NLP) by artificial intelligence remains a pressing problem of our time. The main task of NLP is to create applications that can process and understand natural languages. According to the presented approach to the construction of artificial intelligence agents (AI-agents), processing of natural language should be conducted at two levels: at the bottom, methods of the ascending paradigm are employed, while symbolic methods associated with the descending paradigm are used at the top. To solve these problems, the authors of the present paper propose a new mathematical formalism: associative heterarchical memory (AH-memory), whose structure and functionality are based both on bionic principles and on the achievements of top-down and bottom-up artificial intelligence paradigms.Methods. Natural language recognition algorithms were used in conjunction with various artificial intelligence methods.Results. The problem of character binding as applied to AH-memory was explored by the research group in earlier research. Here, abstract symbol binding was performed using multi-serial integration, eventually converting the primary symbols produced by the program into integrated abstract symbols. The present paper provides a comprehensive description of AH-memory in the form of formulas, along with their explanations and corresponding schemes.Conclusions. The most universal structure of AH-memory is presented. When working with AH-memory, a developer should select from a variety of possible module sets those AH-memory components that support the most successful and efficient functioning of the AI-agent.https://www.rtj-mirea.ru/jour/article/view/563artificial intelligencenatural language processingassociative heterarchical memoryai-agentabstract symbolshypernetpredicate symbol control modelactant role classifierhypergraph
spellingShingle R. V. Dushkin
V. A. Lelekova
V. Y. Stepankov
S. Fadeeva
Structure of associative heterarchical memory
Российский технологический журнал
artificial intelligence
natural language processing
associative heterarchical memory
ai-agent
abstract symbols
hypernet
predicate symbol control model
actant role classifier
hypergraph
title Structure of associative heterarchical memory
title_full Structure of associative heterarchical memory
title_fullStr Structure of associative heterarchical memory
title_full_unstemmed Structure of associative heterarchical memory
title_short Structure of associative heterarchical memory
title_sort structure of associative heterarchical memory
topic artificial intelligence
natural language processing
associative heterarchical memory
ai-agent
abstract symbols
hypernet
predicate symbol control model
actant role classifier
hypergraph
url https://www.rtj-mirea.ru/jour/article/view/563
work_keys_str_mv AT rvdushkin structureofassociativeheterarchicalmemory
AT valelekova structureofassociativeheterarchicalmemory
AT vystepankov structureofassociativeheterarchicalmemory
AT sfadeeva structureofassociativeheterarchicalmemory