Centroid neural network adaptive resonance theory for vector quantization

Author(s): Lin, TC. | Yu, PT. |

Year: 2003

Citation: Signal Processing. Volume 83, Issue 3, 649-654

Abstract: In this paper, a novel unsupervised competitive learning algorithm, called the centroid neural network adaptive resonance theory (CNN-ART) algorithm, is proposed to relieve the dependence on the initial codewords of the codebook in contrast to the conventional algorithms with vector quantization in lossy image compression. The design of the CNN-ART algorithm is mainly based on the adaptive resonance theory structure, and then a gradient-descent-based learning rule is derived so that the CNN-ART algorithm does not require a predetermined schedule for learning rate. Furthermore, the appropriate initial weights obtained by the CNN-ART algorithm can be applied as an initial codebook for the Linde-Buzo-Gray (LBG) algorithm such that the compression performance can be greatly improved. In this paper, the extensive simulations demonstrate that the CNN-ART algorithm does outperform other algorithms like LBG, self-organizing feature map and differential competitive learning.

Topics: Machine Learning, Models: Modified ART,

PDF download

Cross References