add HingeLossLayer for one-vs-all hinge loss

add HingeLossLayer for one-vs-all hinge loss

This layer implements a "one-vs-all" hinge loss, (1/n) sum_ij max(0, 1 -
y_ij x_ij), with bottom blob x_ij (i ranging over examples and j over
classes), and y_ij = +1/-1 indicating the label. No regularization is
included, since regularization is done via weight decay or using the
parameters of another layer. The gradient is taken to be zero at the
hinge point. This commit only provides the CPU implementation.