Neural Networks: Project-1 Fall, 2002
to device a classifier to perform document classification using the following
(i) the minimal-distance linear classifier, and
(ii) the two-layer feedforward neural network.
There are 303 text documents, each of which belongs to one of the 15 classes.
These documents are divided into two sets, one for training and the other one for testing.
The documents for training are shown in list "TrainList.txt", while the documents for
testing are in list "TestList.txt". The text documents are provided with three formats:
the word identities, the syllable identities, and the GB-coded text.