Apply a support vector machine to classify hand-written digits. SVM algorithm implementation provided by e1071 R package.
The digit data set contains two files: both files are text files. Each file contains a matrix with one data point (=vector of length 256) per row. The 256-vector in each row represents a 16×16 image of a handwritten number. The data contains two classes--the digits 5 and 6 so they can be labeled as -1 and +1, respectively.
Objectives:
-
Train linear SVM with soft margin. Cross-validate the margin parameter
-
Train a SVM with soft margin andRBF kernel.
-
Compute the misclassification rate for both algorithms on test set.