Evolutionary Neural Gas (ENG): A Model of Self Organizing Network from Input Categorization

TL;DR

The paper introduces Evolutionary Neural Gas (ENG), a flexible self-organizing network model that adapts to noisy, fuzzy inputs and evolves into a scale-free graph, mimicking biological systems more closely.

Contribution

It proposes a novel ENG model with no topological constraints, using probabilistic laws for adaptation, and demonstrates its evolution into a scale-free network structure.

Findings

ENG evolves as a scale-free graph

The model adapts quickly to environmental changes

Network behavior is justified in a physical sense

Abstract

Despite their claimed biological plausibility, most self organizing networks have strict topological constraints and consequently they cannot take into account a wide range of external stimuli. Furthermore their evolution is conditioned by deterministic laws which often are not correlated with the structural parameters and the global status of the network, as it should happen in a real biological system. In nature the environmental inputs are noise affected and fuzzy. Which thing sets the problem to investigate the possibility of emergent behaviour in a not strictly constrained net and subjected to different inputs. It is here presented a new model of Evolutionary Neural Gas (ENG) with any topological constraints, trained by probabilistic laws depending on the local distortion errors and the network dimension. The network is considered as a population of nodes that coexist in an ecosystem sharing local and global resources. Those particular features allow the network to quickly adapt to the environment, according to its dimensions. The ENG model analysis shows that the net evolves as a scale-free graph, and justifies in a deeply physical sense- the term gas here used.