Optimally integrated adaptive learning
- 1 January 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 609-612 vol.1
- https://doi.org/10.1109/icassp.1993.319192
Abstract
A new self-organized learning algorithm is proposed that is well suited for the problem of image compression. The network consists of a number of modules corresponding to different classes of input data. Each module consists of an orthonormal linear transformation whose weights are calculated during an initial training period. As the network is trained, each input signal x is classified according to a competitive learning scheme based on the maximum norm of the signal's projection under the class transformation. The classification is optimal in the sense that it minimizes the square error. The class transformation weights are updated according to a Hebbian learning rule which converges to the optimal Karhunen-Loeve transformation (KLT) for each class. The performance of the resulting adaptive network is shown to be superior to that of the optimal non-adaptive linear transformation.Keywords
This publication has 7 references indexed in Scilit:
- A neural network learning algorithm for adaptive principal component extraction (APEX)Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Adaptive distributed orthogonalization processing for principal components analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Optimal unsupervised learning in a single-layer linear feedforward neural networkNeural Networks, 1989
- Digital PicturesPublished by Springer Nature ,1988
- Simplified neuron model as a principal component analyzerJournal of Mathematical Biology, 1982
- Image data compression: A reviewProceedings of the IEEE, 1981
- Picture coding: A reviewProceedings of the IEEE, 1980