View on GitHub

GHNG

The Growing Hierarchical Neural Gas Self-Organizing Neural Network (GHNG)

GHNG

The Growing Hierarchical Neural Gas Self-Organizing Neural Network (GHNG) is a hierarchical extension of the Growing Neural Gas (GNG) where a tree of modified GNGs is learned from the input dataset, so that hierarchical data can be analyzed without the restriction of fixed lattice topologies among the neurons.

This work was published in IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS journal as The Growing Hierarchical Neural Gas Self-Organizing Neural Network.

Run the demo

You may want to start by running some of the ghng_demo*.m scripts.

GHNG self-organization for the two-dimensional ’X’ letter input distribution

GHNG color quantization for the baboon image

The contents of this zip file are provided without any warranty. They are intended for evaluational purposes only. Any suggestions and bug reports will be welcome.

Citation

Please, cite this work as:

E. J. Palomo and E. López-Rubio, “The Growing Hierarchical Neural Gas Self-Organizing Neural Network,” in IEEE Transactions on Neural Networks and Learning Systems, vol. 28, no. 9, pp. 2000-2009, Sept. 2017, doi: 10.1109/TNNLS.2016.2570124.