Knowledge-Based Systems

212 Chapter 7 ConneCtionist Models

For example, in character recognition, to verify whether a given pattern

is character “X” or some other character is an easy classification problem.

The basic principle is to recognize and classify given patterns to much fewer

groups of patterns. The latter will be the output of the network for this type

of application. The network can be trained using sample patterns and their

correct answers. When the network is well trained, it gives correct answers

for not only the sample patterns, but also for new similar patterns. As men-

tioned, the input can be of any form, not just a visual image.

We have to consider ...