ARTgrid: a two-level learning architecture based on adaptive resonance theory

Švaco, Marko and Jerbić, Bojan and Šuligoj, Filip (2014) ARTgrid: a two-level learning architecture based on adaptive resonance theory. = ARTgrid: a two-level learning architecture based on adaptive resonance theory. Advances in Artificial Neural Systems, 2014. pp. 1-9. ISSN 1687-7594. Vrsta rada: ["eprint_fieldopt_article_type_article" not defined]. . Točan broj autora: 3.

[img]
Preview
Text
Jerbić, Bojan_ARTgrid A Two Level Learning Architecture Based on Adaptive Resonance Theory.pdf - Published Version Jezik dokumenta:English

Download (2MB) | Preview
Official URL: http://www.hindawi.com/journals/aans/2014/185492/

Abstract

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.

Item Type: Article (["eprint_fieldopt_article_type_article" not defined])
Keywords (Croatian): machine learning, adaptive resonance theory, ARTgrid
Subjects: TECHNICAL SCIENCE > Mechanical Engineering
Divisions: 900 Department of Robotics and Production System Automation > 920 Chair of Manufacturing and Assembly System Planning
Indexed in Web of Science: No
Indexed in Current Contents: No
Date Deposited: 19 Sep 2016 14:30
Last Modified: 25 Oct 2018 11:22
URI: http://repozitorij.fsb.hr/id/eprint/6376

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year