The neural gas is a simple algorithm for finding optimal data representations based on feature vectors. The algorithm was coined "neural gas" because of the dynamics of the feature vectors during the adaptation process, which distribute themselves like a gas within the data space.
Neural gas is an artificial neural network, inspired by the self-organizing map. The neural gas is a simple algorithm for finding optimal data representations based on feature vectors.
Growing Neural Gas (GNG) was introduced by Fritzke as an incremental unsupervised neural network for non-temporal data. Starting with two neurons GNG grows in regular time intervals up to a maximal size. Connections between neurons are created by topology preserving Competitive Hebbian Learning.