Fast training of neural networks for image compression

Authors:
Yevgeniy Bodyanskiy;Paul Grimm;Sergey Mashtalir;Vladimir Vinarski
Affiliations:
Kharkiv National University of Radio Electronics, Computer Science faculty, Kharkiv, Ukraine;University of Applied Sciences, Erfurt, Germany;Kharkiv National University of Radio Electronics, Computer Science faculty, Kharkiv, Ukraine;University of Applied Sciences and Arts, Hannover, Germany
Venue:
ICDM'10 Proceedings of the 10th industrial conference on Advances in data mining: applications and theoretical aspects
Year:
2010

Citing 5
Cited 0

Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Self-Organizing Maps

Self-Organizing Maps
A new learning algorithm for a forecasting neuro-fuzzy network

Integrated Computer-Aided Engineering
Fast principal component extraction by a weighted informationcriterion

IEEE Transactions on Signal Processing
Fast subspace tracking and neural network learning by a novelinformation criterion

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper considers the problem of image compression by using artificial neural networks (ANN). The main concept of this approach is the reduction of the original feature spaces, what allows us to eliminate the image redundancy and accordingly leads to their compression. Two variants of the neural networks: two layers ANN with the self-learning algorithm based on the weighted informational criterion and auto-associative four-layers feedforward network have been proposed and analyzed.