60756

Автор(ы): 

Автор(ов): 

2

Параметры публикации

Тип публикации: 

Доклад

Название: 

Indextron

ISBN/ISSN: 

978-989-758-486-2/2184-4313

DOI: 

10.5220/0010180301430149

Наименование конференции: 

  • 10th International Conference on Pattern Recognition Application and Methods (ICPRAM 2021, Vienna)

Наименование источника: 

  • Proceedings of 10th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2021, Vienna)

Обозначение и номер тома: 

volume 1

Город: 

  • Vienna

Издательство: 

  • SCITEPRESS

Год издания: 

2021

Страницы: 

143-149
Аннотация
How to do pattern recognition without artificial neural networks, Bayesian classifiers, vector support machines and other mechanisms that are widely used for machine learning? The problem with pattern recognition machines is time and energy demanding training because lots of coefficients need to be worked out. The paper introduces an indexing model that performs training by memorizing inverse patterns mostly avoiding any calculations. The computational experiments indicate the potential of the indexing model for artificial intelligence applications and, possibly, its relevance to neurobiological studies as well

Библиографическая ссылка: 

Михайлов А.М., Каравай М.Ф. Indextron / Proceedings of 10th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2021, Vienna). Vienna: SCITEPRESS, 2021. volume 1. С. 143-149.