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

Authors:
Enrique Mérida-Casermeiro;Domingo López-Rodríguez;Gloria Galán-Marín;Juan M. Ortiz-De-Lazcano-Lobato
Affiliations:
Department of Applied Mathematics, University of Málaga, Málaga, Spain;Department of Applied Mathematics, University of Málaga, Málaga, Spain;Department of Electronics and Electromechanical Engineering, University of Extremadura, Badajoz, Spain;Department of Computer Science and Artificial Intelligence, University of Málaga, Málaga, Spain
Venue:
ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part I
Year:
2007

Citing 6
Cited 1

Competitive learning algorithms for vector quantization

Neural Networks
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
Expansive and Competitive Learning for Vector Quantization

Neural Processing Letters
Expansive and Competitive Neural Networks

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
A self-organizing network for hyperellipsoidal clustering (HEC)

IEEE Transactions on Neural Networks

A Neighborhood-Based Competitive Network for Video Segmentation and Object Detection

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work, a general framework for developing learning rules with an added term (perturbation term) is presented. Many learning rules commonly cited in the specialized literature can be derived from this general framework. This framework allows us to introduce some knowledge about vector quantization (as an optimization problem) in the distortion function in order to derive a new learning rule that uses that information to avoid certain local minima of the distortion function, leading to better performance than classical models. Computational experiments in image compression show that our proposed rule, derived from this general framework, can achieve better results than simple competitive learning and other models, with codebooks of less distortion.