Applying Probabilistic Neural Networks to the Multifont Recognition Problem with Large Training Set

May 1999

Proceedings of the Twelfth International Florida Artificial Intelligence Research Society Conference (FLAIRS 1999)

Volume

Proceedings of the Twelfth International Florida Artificial Intelligence Research Society Conference (FLAIRS 1999)

All Papers

Neural networks are very often applied to the pattern recognition problem. In 1990 D. Specht introduced a special class of Probabilistic Neural Networks which were unnoticed in the computational practice due to their extremely large computer memory requirement. In this note we present and discuss results of experiments assessing the usability of Probabilistic Neural Networks to the multifont recognition problem for large size of the training set.