Repeat Problem P10.9, but use the numerals "1", "2" and "4", instead of the letters "T", "G" and "F". Test the trained network on each reference pattern and on noisy patterns. Discuss the sensitivity of the network. (Use the Neural Network Design Demonstration Linear Pattern Classification (nnd10lc).)
Problem P10.9
Repeat the work of Widrow and Hoff on a pattern recognition problem from their classic 1960 paper [WiHo60]. They wanted to design a recognition system that would classify the six patterns shown in Figure P10.11.
These patterns represent the letters T, G and F, in an original form on the top and in a shifted form on the bottom. The targets for these letters (in their original and shifted forms) are +60, 0 and -60, respectively. (The values of 60, 0 and -60 were nice for use on the face of a meter that Widrow and Hoff used to display their network output.) The objective is to train a network so that it will classify the six patterns into the appropriate T, G or F groups.