Novel arti cial intelligence methods are used to classify 16x16 pixel regions (obtained from Advanced Very High Resolution Radiometer (AVHRR) images) in terms of cloud type (e.g., stratus, cumulus, etc.). We previously reported that intelligent feature selection methods, combined with nearest neighbor classi ers, can dramatically improve classi cation accuracy on this task. Our subsequent analy...

1. Because the length of code is much less than the number of words, by casting the problem of predicting word to predicting each bit, we can reduce the size of the problem dramatically. Accordingly, the amount of data needed for training can be reduced. 2. By using error correcting output coding, it is possible that we can get better generalization performance on test data. 3. The distributed ...