2011 Special Issue: A hierarchical ART network for the stable incremental learning of topological structures and associations from noisy data

Authors:
Marko Tscherepanow;Marco Kortkamp;Marc Kammer
Affiliations:
Bielefeld University, Applied Informatics, Universitätsstraíe 25, 33615 Bielefeld, Germany;Bielefeld University, Applied Informatics, Universitätsstraíe 25, 33615 Bielefeld, Germany;Bielefeld University, Applied Informatics, Universitätsstraíe 25, 33615 Bielefeld, Germany and Bielefeld University, Cognitive Interaction Technology-Center of Excellence, Universitä ...
Venue:
Neural Networks
Year:
2011

Citing 11
Cited 0

Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
An incremental network for on-line unsupervised classification and topology learning

Neural Networks
An enhanced self-organizing incremental neural network for online unsupervised learning

Neural Networks
Using Alpha-Beta Associative Memories to Learn and Recall RGB Images

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
2009 Special Issue: A new bidirectional heteroassociative memory encompassing correlational, competitive and topological properties

Neural Networks
Associative memory for online learning in noisy environments using self-organizing incremental neural network

IEEE Transactions on Neural Networks
TopoART: a topology learning hierarchical ART network

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Continuous visual codebooks with a limited branching tree growing neural gas

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
A perceptual memory system for affordance learning in humanoid robots

ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
Accurate and Fast Off and Online Fuzzy ARTMAP-Based Image Classification With Application to Genetic Abnormality Diagnosis

IEEE Transactions on Neural Networks
Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this article, a novel unsupervised neural network combining elements from Adaptive Resonance Theory and topology-learning neural networks is presented. It enables stable on-line clustering of stationary and non-stationary input data by learning their inherent topology. Here, two network components representing two different levels of detail are trained simultaneously. By virtue of several filtering mechanisms, the sensitivity to noise is diminished, which renders the proposed network suitable for the application to real-world problems. Furthermore, we demonstrate that this network constitutes an excellent basis to learn and recall associations between real-world associative keys. Its incremental nature ensures that the capacity of the corresponding associative memory fits the amount of knowledge to be learnt. Moreover, the formed clusters efficiently represent the relations between the keys, even if noisy data is used for training. In addition, we present an iterative recall mechanism to retrieve stored information based on one of the associative keys used for training. As different levels of detail are learnt, the recall can be performed with different degrees of accuracy.