Comparison of two different PNN training approaches for satellite cloud data classification

Authors
Tian, B Azimi-Sadjadi, MR
Citation
B. Tian et Mr. Azimi-sadjadi, Comparison of two different PNN training approaches for satellite cloud data classification, IEEE NEURAL, 12(1), 2001, pp. 164-168
Citations number
11
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
IEEE TRANSACTIONS ON NEURAL NETWORKS
ISSN journal
10459227 → ACNP
Volume
12
Issue
1
Year of publication
2001
Pages
164 - 168
Database
ISI
SICI code
1045-9227(200101)12:1<164:COTDPT>2.0.ZU;2-Z
Abstract
This paper presents a training algorithm for probabilistic neural networks (PNNs) using the minimum classification error (MCE) criterion. A comparison is made between the MCE training scheme and the widely used maximum likeli hood (ML) learning on a cloud classification problem using satellite imager y data.