On the Characteristics of Growing Cell Structures (GCS) Neural Network

Authors:
Jung-Hua Wang;Wei-Der Sun
Affiliations:
Department of Electrical Engineering, National Taiwan Ocean University, 2 Peining Rd. Keelung, Taiwan, e-mail: b0141@ind.ntou.edu.tw;Department of Electrical Engineering, National Taiwan Ocean University, 2 Peining Rd. Keelung, Taiwan, e-mail: b0141@ind.ntou.edu.tw
Venue:
Neural Processing Letters
Year:
1999

Citing 6
Cited 1

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Topology representing networks

Neural Networks
Growing cell structures—a self-organizing network for unsupervised and supervised learning

Neural Networks
Kernel-based equiprobabilistic topographic map formation

Neural Computation
A Mathematical Theory of Communication

A Mathematical Theory of Communication
Harmonic competition: a self-organizing multiple criteria optimization

IEEE Transactions on Neural Networks

Self-organizing maps with a time-varying structure

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, aself-developing neural network model, namely theGrowing Cell Structures (GCS) is characterized. In GCSeach node (or cell) is associated with a localresource counter τ (t). We show thatGCS has the conservation property by which thesummation of all resource counters always equalss(1 - α)/α, thereby sis the increment added to τ (t) of the wining node after eachinput presentation and α (0