Abstract
A competitive learning algorithm for the parametric classification of Gaussian sources is presented in this letter. The algorithm iteratively estimates the mean and prior probability of each class during the training. Bayes rule is then used for classification based on the estimated information. Simulation results show that the proposed algorithm outperforms k-means and LVQ algorithms for the parametric classification.
Original language | English |
---|---|
Pages (from-to) | 375-380 |
Number of pages | 6 |
Journal | Pattern Recognition Letters |
Volume | 21 |
Issue number | 5 |
DOIs | |
Publication status | Published - 2000 May |
Externally published | Yes |
Keywords
- Competitive learning
- Maximum likelihood estimation
- Neural networks
- Parametric classification
- Pattern recognition
ASJC Scopus subject areas
- Software
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence