Publication:
One Possibility of a Neuro-Symbolic Integration

Дата
2022
Авторы
Samsonovich, A. V.
Journal Title
Journal ISSN
Volume Title
Издатель
Научные группы
Организационные подразделения
OrgUnit Logo
Организационная единица
Институт интеллектуальных кибернетических систем
Цель ИИКС и стратегия развития - это подготовка кадров, способных противостоять современным угрозам и вызовам, обладающих знаниями и компетенциями в области кибернетики, информационной и финансовой безопасности для решения задач разработки базового программного обеспечения, повышения защищенности критически важных информационных систем и противодействия отмыванию денег, полученных преступным путем, и финансированию терроризма.
Выпуск журнала
Аннотация
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Deep learning (DL) technologies automate the labor of theoreticians, developers, and programmers, that is otherwise needed to design knowledge representations and algorithms for each particular domain. At the same time, DL has limitations rooted in the statistical nature of the method, which largely ignores the available domain knowledge. An example of a DL-hard domain is human social-emotional behavior. In contrast, biologically inspired cognitive architectures (BICA) are based on the scientific knowledge accumulated in cognitive and neuro-sciences, and therefore can be successful in generating believable socially-emotional behavior, although at great expense of intellectual human labor. The challenge is to integrate the two approaches, adding their strengths and compensating their weaknesses. Here a particular form of such integration is proposed, that also involves methods of evolutionary programming. The expected result could be a self-developing artificial socially-emotional intelligence, capable of growing autonomously to the human level and beyond. Potential future applications of the method can be expected to have a global impact on the society.
Описание
Ключевые слова
Цитирование
Samsonovich, A. V. One Possibility of a Neuro-Symbolic Integration / Samsonovich, A.V. // Studies in Computational Intelligence. - 2022. - 1032 SCI. - P. 428-437. - 10.1007/978-3-030-96993-6_47
URI
https://www.doi.org/10.1007/978-3-030-96993-6_47
 https://www.scopus.com/record/display.uri?eid=2-s2.0-85127619514&origin=resultslist
 http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000833484200047
 https://openrepository.mephi.ru/handle/123456789/28970
Коллекции
Публикации