WestminsterResearch will not be accepting deposits until 16th March 2015. This is to allow for a system upgrade and server migration.

Autonomous growing neural gas for applications with time constraint: optimal parameter estimation

Garcia Rodriguez, Jose and Angelopoulou, Anastassia and García-Chamizo, Juan Manuel and Psarrou, Alexandra and Orts Escolano, Sergio and Morell Gimenez, Vicente (2012) Autonomous growing neural gas for applications with time constraint: optimal parameter estimation. Neural Networks, 32 . pp. 196-208. ISSN 0893-6080

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1016/j.neunet.2012.02.032


This paper aims to address the ability of self-organizing neural network models to manage real-time applications. Specifically, we introduce fAGNG (fast Autonomous Growing Neural Gas), a modified learning algorithm for the incremental model Growing Neural Gas(GNG)network. The Growing Neural Gas network with its attributes of growth, flexibility, rapid adaptation, and excellent quality of representation of the input space makes it a suitable model for real timeapplications. However, under time constraints GNG fails to produce the optimal topological map for any input data set. In contrast to existing algorithms, the proposed fAGNG algorithm introduces multiple neurons per iteration. The number of neurons inserted and input data generated is controlled autonomous and dynamically based on a priory or online learnt model. A detailed study of the topological preservation and quality of representation depending on the neuralnetworkparameter selection has been developed to find the best alternatives to represent different linear and non-linear input spaces under time restrictions or specific quality of representation requirements.

Item Type:Article
Research Community:University of Westminster > Electronics and Computer Science, School of
ID Code:10413
Deposited On:24 Apr 2012 10:35
Last Modified:14 May 2013 12:24

Repository Staff Only: item control page