Napredna pretraga

Pregled bibliografske jedinice broj: 738958

ARTgrid: A Two-Level Learning Architecture Based on Adaptive Resonance Theory


Švaco, Marko; Jerbić, Bojan; Šuligoj Filip
ARTgrid: A Two-Level Learning Architecture Based on Adaptive Resonance Theory // Advances in Artificial Neural Systems, 2014 (2014), 1-9 doi:10.1155/2014/185492 (podatak o recenziji nije dostupan, članak, znanstveni)


Naslov
ARTgrid: A Two-Level Learning Architecture Based on Adaptive Resonance Theory

Autori
Švaco, Marko ; Jerbić, Bojan ; Šuligoj Filip

Izvornik
Advances in Artificial Neural Systems (1687-7594) 2014 (2014); 1-9

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Machine learning; Adaptive resonance theory; ARTgrid

Sažetak
This paper proposes a novel neural network architecture based on adaptive resonance theory (ART) called ARTgrid that can perform both online and offline clustering of 2D object structures. The main novelty of the proposed architecture is a two-level categorization and search mechanism that can enhance computation speed while maintaining high performance in cases of higher vigilance values. ARTgrid is developed for specific robotic applications for work in unstructured environments with diverse work objects. For that reason simulations are conducted on random generated data which represents actualmanipulation objects, that is, their respective 2D structures. ARTgrid verification is done through comparison in clustering speed with the fuzzy ART algorithm and Adaptive Fuzzy Shadow (AFS) network. Simulation results show that by applying higher vigilance values clustering performance of ARTgrid is considerably better, while lower vigilance values produce comparable results with the original fuzzy ART algorithm.

Izvorni jezik
Engleski

Znanstvena područja
Matematika, Računarstvo, Strojarstvo



POVEZANOST RADA


Projekt / tema
120-1201948-1941 - AUTONOMNA VIŠEAGENTNA AUTOMATSKA MONTAŽA (Bojan Jerbić, )
HRZZ-IP-2013-11-4192 - Novi koncept primijenjene kognitivne robotike u kliničkoj neuroznanosti (Bojan Jerbić, )

Ustanove
Fakultet strojarstva i brodogradnje, Zagreb

Uključenost u ostale bibliografske baze podataka:


  • Biological Sciences
  • Computer and Information Systems Abstracts
  • Google Scholar
  • Chemical Abstracts Service


Citati