Szczegóły publikacji
Opis bibliograficzny
Associative pattern matching and inference using associative graph data structures / Adrian HORZYK, Agata Czajkowska // W: Artificial Intelligence and Soft Computing : 18th International conference, ICAISC 2019 : Zakopane, Poland, June 16-20 2019 : proceedings, Pt. 2 / eds. Leszek Rutkowski, Rafał Scherer, Marcin Korytkowski, Witold Pedrycz, Ryszard Tadeusiewicz, Jacek M. Zurada. — Cham : Springer, cop. 2019. — (Lecture Notes in Computer Science ; ISSN 0302-9743. Lecture Notes in Artificial Intelligence ; LNAI 11509). — ISBN: 978-3-030-20914-8; e-ISBN: 978-3-030-20915-5. — S. 371-383. — Bibliogr. s. 382-383, Abstr.
Autorzy (2)
- AGHHorzyk Adrian
- Czajkowska A.
Słowa kluczowe
Dane bibliometryczne
ID BaDAP | 123146 |
---|---|
Data dodania do BaDAP | 2019-07-23 |
Tekst źródłowy | URL |
DOI | 10.1007/978-3-030-20915-5_34 |
Rok publikacji | 2019 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Wydawca | Springer |
Konferencja | 18th International conference Artificial Intelligence and Soft Computing |
Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
Inference on the still growing amount of data is a challenging problem that must be solved to operate efficiently and mine Big Data sources successfully and in a sensible time. This paper introduces a new inference method based on associative recalling of data and their relationships stored in associative graph data structures (AGDS) used for pattern matching for given criteria. These structures represent a richer set of relationships than popular tabular structures do because of their natural limitations. They recall relationships and related data faster than the time-consuming search algorithms based on many loops and conditions on tabular structures. It explains why brain processes trigger information so quickly, outperforming solution based on the Turing Machine and contemporary fast processors. The presented associative inference can work in constant time thanks to the specific data organization, access and direct representation of more relationships in AGDS structures than in the commonly used tabular structures. © Springer Nature Switzerland AG 2019.