Title :
Comparison of two different PNN training approaches for satellite cloud data classification
Author :
Tian, Bin ; Azimi-Sadjadi, Mahmood R.
Author_Institution :
Dept. of Electr. & Comput. Eng., Colorado State Univ., Fort Collins, CO, USA
fDate :
1/1/2001 12:00:00 AM
Abstract :
Presents a training algorithm for probabilistic neural networks (PNN) using the minimum classification error (MCE) criterion. A comparison is made between the MCE training scheme and the widely used maximum likelihood (ML) learning on a cloud classification problem using satellite imagery data
Keywords :
clouds; learning (artificial intelligence); maximum likelihood estimation; minimisation; neural nets; pattern classification; probability; remote sensing; MCE criterion; MCE training scheme; ML learning; PNN training approaches; maximum likelihood learning; minimum classification error criterion; probabilistic neural networks; satellite cloud data classification; satellite imagery data; Atmospheric modeling; Clouds; Maximum likelihood estimation; Neural networks; Neurons; Pattern recognition; Probability density function; Robustness; Satellites; Training data;
Journal_Title :
Neural Networks, IEEE Transactions on
