Proceedings ArticleDOI
CFART: a multi-resolutional adaptive resonance system
Hai-Lung Hung,Hong-Yuan Mark Liao,Chwen-Jye Sze,Shing-Jong Lin,Wei-Chung Lin,Kuo-Chin Fan +5 more
- Vol. 2, pp 1312-1317
Reads0
Chats0
TLDR
A cascade fuzzy ART (CFART) network is developed and applied to 3D object recognition, capable of acting as an extensible database, providing a multi-resolutional representation of 3D objects.Abstract:
In this paper, a cascade fuzzy ART (CFART) network is developed and applied to 3D object recognition. The proposed CFART network contains multiple layers which can express a hierarchical representation of an input pattern. The learning processes of the proposed network are unsupervised and self-organizing, which include a top-down search process and a bottom-up learning process. The proposed CFART can accept both binary and analog inputs. With fast learning and categorization capabilities, the proposed network is capable of acting as an extensible database, providing a multi-resolutional representation of 3D objects. In the experiments, we use superquadrics as a demonstration example.read more
Citations
More filters
Posted Content
Distributed dual vigilance fuzzy adaptive resonance theory learns online, retrieves arbitrarily-shaped clusters, and mitigates order dependence
TL;DR: Performance comparisons to non-ART-based clustering algorithms show that DDVFA was also statistically equivalent to the non-incremental methods of density-based spatial clustering of applications with noise, single linkage hierarchical agglomerative clustering (SL-HAC), and k-means, while retaining the appealing properties of ART.
Journal ArticleDOI
Distributed dual vigilance fuzzy adaptive resonance theory learns online, retrieves arbitrarily-shaped clusters, and mitigates order dependence.
TL;DR: The distributed dual vigilance fuzzy clustering (DDVFA) as discussed by the authors is a modular adaptive resonance theory (ART)-based modular architecture for unsupervised learning, which is equipped with distributed higher-order activation and match functions and a dual vigilance mechanism.
Dissertation
Multi-label Classification with Multiple Class Ontologies
TL;DR: The main contribution of the thesis is the extensive examination of using rare association rules for the improvement of multi-label predictions in the setup of cross-ontology classification, especially the proposed approach called Multi-label Improvement with Rare Association Rules (MIRAR).
References
More filters
Journal ArticleDOI
A massively parallel architecture for a self-organizing neural pattern recognition machine
TL;DR: A neural network architecture for the learning of recognition categories is derived which circumvents the noise, saturation, capacity, orthogonality, and linear predictability constraints that limit the codes which can be stably learned by alternative recognition models.
PatentDOI
System for self-organization of stable category recognition codes for analog input patterns
TL;DR: ART 2, a class of adaptive resonance architectures which rapidly self-organize pattern recognition categories in response to arbitrary sequences of either analog or binary input patterns, is introduced.
Journal ArticleDOI
Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system
TL;DR: This paper aims to demonstrate the efforts towards in-situ applicability of EMMARM, which aims to provide real-time information about concrete mechanical properties such as E-modulus and compressive strength.
Journal ArticleDOI
An ART-based modular architecture for learning hierarchical clusterings
TL;DR: A neural architecture (HART for “Hierarchical ART”) that is capable of learning hierarchical clusterings of arbitrary input sequences and the notion of effective vigilance is introduced to refer to the vigilance level of multiple ART modules in a HART network.