Fast image representation with GPU-based growing neural gas

Authors:
José García-Rodríguez;Anastassia Angelopoulou;Vicente Morell;Sergio Orts;Alexandra Psarrou;Juan Manuel García-Chamizo
Affiliations:
Dept. of Computing Technology, University of Alicante, Alicante, Spain;Dept. of Computer Science & Software Engineering, University of Westminster, United Kingdom;Dept. of Computing Technology, University of Alicante, Alicante, Spain;Dept. of Computing Technology, University of Alicante, Alicante, Spain;Dept. of Computer Science & Software Engineering, University of Westminster, United Kingdom;Dept. of Computing Technology, University of Alicante, Alicante, Spain
Venue:
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part II
Year:
2011

Citing 3
Cited 1

Topology representing networks

Neural Networks
Self-organizing maps

Self-organizing maps
Three-dimensional surface reconstruction using meshing growing neural gas (MGNG)

The Visual Computer: International Journal of Computer Graphics

GPGPU implementation of growing neural gas: Application to 3D scene reconstruction

Journal of Parallel and Distributed Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper aims to address the ability of self-organizing neural network models to manage real-time applications. Specifically, we introduce a Graphics Processing Unit (GPU) implementation with Compute Unified Device Architecture (CUDA) of the Growing Neural Gas (GNG) network. The Growing Neural Gas network with its attributes of growth, flexibility, rapid adaptation, and excellent quality representation of the input space makes it a suitable model for real time applications. In contrast to existing algorithms the proposed GPU implementation allow the acceleration keeping good quality of representation. Comparative experiments using iterative, parallel and hybrid implementation are carried out to demonstrate the effectiveness of CUDA implementation in representing linear and non-linear input spaces under time restrictions.