The Growing Hierarchical Neural Gas Self-Organizing Neural Network

The growing neural gas (GNG) self-organizing neural network stands as one of the most successful examples of unsupervised learning of a graph of processing units. Despite its success, little attention has been devoted to its extension to a hierarchical model, unlike other models such as the self-org...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems Vol. 28; no. 9; pp. 2000 - 2009
Main Authors: Palomo, Esteban J., Lopez-Rubio, Ezequiel
Format: Journal Article
Language:English
Published: United States IEEE 01.09.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Hierarchical model
Learning systems
Neural networks
Neurons
Prototypes
Quantization (signal)
Self organizing maps
self-organization
Topology
Training
unsupervised learning
Vector quantization
ISSN:2162-237X, 2162-2388
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The growing neural gas (GNG) self-organizing neural network stands as one of the most successful examples of unsupervised learning of a graph of processing units. Despite its success, little attention has been devoted to its extension to a hierarchical model, unlike other models such as the self-organizing map, which has many hierarchical versions. Here, a hierarchical GNG is presented, which is designed to learn a tree of graphs. Moreover, the original GNG algorithm is improved by a distinction between a growth phase where more units are added until no significant improvement in the quantization error is obtained, and a convergence phase where no unit creation is allowed. This means that a principled mechanism is established to control the growth of the structure. Experiments are reported, which demonstrate the self-organization and hierarchy learning abilities of our approach and its performance for vector quantization applications.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2016.2570124