Representation of “Natural” Concepts and Classes by a Hypernet Lattice of (Probabilistic) Formal Concepts

Результат исследования: Публикации в книгах, отчётах, сборниках, трудах конференцийстатья в сборнике материалов конференциинаучнаярецензирование

Аннотация

In previous works, a probabilistic generalization of formal concepts was developed that is resistant to noise and is capable of restoring formal concepts. In this paper, we show that probabilistic formal concepts have a deeper meaning than the restoration of formal concepts. Probabilistic formal concepts model “natural” concepts explored in cognitive sciences and “natural” classes explored in the “natural” classification. The hyper network of probabilistic formal concepts reflects the hierarchical structure of complex patterns – a hierarchy of secondary, increasingly complex features that are found as a result of deep learning. This hierarchy, obtained by logical-probabilistic methods, in addition to being “natural”, is also explanatory, since it can give descriptions of its classes in logical-probabilistic terms. Thus, the hierarchy of probabilistic formal concepts discovered on complex images yields logical-probabilistic deep learning. The vertices of the hyper simplexes of the hyper network of probabilistic formal concepts reflect the content of “natural” concepts and classes, as they are inextricably linked with the underlying features. These vertices determine the meanings of “natural” concepts and classes, which are not reducible to the features that form them.

Язык оригиналаанглийский
Название основной публикацииAdvances in Cognitive Research, Artificial Intelligence and Neuroinformatics - Proceedings of the 9th International Conference on Cognitive Sciences, Intercognsci-2020
РедакторыBoris M. Velichkovsky, Pavel M. Balaban, Vadim L. Ushakov
ИздательSpringer Science and Business Media Deutschland GmbH
Страницы671-676
Число страниц6
ISBN (печатное издание)9783030716363
DOI
СостояниеОпубликовано - 2021
Событие9th International Conference on Cognitive Sciences, Intercognsci 2020 - Moscow, Российская Федерация
Продолжительность: 10 окт 202016 окт 2020

Серия публикаций

НазваниеAdvances in Intelligent Systems and Computing
Том1358 AIST
ISSN (печатное издание)2194-5357
ISSN (электронное издание)2194-5365

Конференция

Конференция9th International Conference on Cognitive Sciences, Intercognsci 2020
СтранаРоссийская Федерация
ГородMoscow
Период10.10.202016.10.2020

Предметные области OECD FOS+WOS

  • 1.02 КОМПЬЮТЕРНЫЕ И ИНФОРМАЦИОННЫЕ НАУКИ

Fingerprint

Подробные сведения о темах исследования «Representation of “Natural” Concepts and Classes by a Hypernet Lattice of (Probabilistic) Formal Concepts». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать