In this example a two-class linear support vector machine classifier is trained
on a randomly generated data. As training algorithm the LIBLINEAR solver is used
with the SVM regularization parameter C=0.1 and the bias term in the
classification rule switched off. The solver iterates until it reaches the
epsilon-precise (epsilon=1e-3) solution. The example also shows how to compute
classifier outputs on the training examples and the value of the primal SVM
objective function.

For more details on LIBLINEAR see
    http://www.csie.ntu.edu.tw/~cjlin/liblinear/
