Expansive and Competitive Neural Networks

Authors:
José Antonio Gómez-Ruiz;José Muñoz-Perez;Ezequiel López-Rubio;M. A. Garcia-Bernal
Affiliations:
-;-;-;-
Venue:
IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
Year:
2001

Citing 4
Cited 1

Competitive learning algorithms for vector quantization

Neural Networks
Introduction to the theory of neural computation

Introduction to the theory of neural computation
A new competitive learning approach based on an equidistortion principle for designing optimal vector quantizers

Neural Networks
Color Image Segmentation using Competitive Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence

Improved Production of Competitive Learning Rules with an Additional Term for Vector Quantization

ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we develop a necessary and sufficient condition for a local minimum to be a global minimum to the vector quantization problem and present a competitive learning algorithm based on this condition which has two learning terms; the first term regulates the force of attraction between the synaptic weight vectors and the input patterns in order to reach a local minimum while the second term regulates the repulsion between the synaptic weight vectors and the input's gravity center, favoring convergence to the global minimum. This algorithm leads to optimal or near optimal solutions and it allows the network to escape from local minima during trainning. Experimental results in image compression demonstrate that it outperforms the simple competitive learning algorithm, giving better codebooks.