In formulation (3), there is a factor \gamma. This parameter is setted to prevent the hinge loss to be 0. However, I haven't find this parameter in the code.
The 0 loss is quite common in deep learning and this phenomenon is usually called "overfit". In deep learning, people usually use dropout to prevent the loss from getting to zero too early.
In formulation (3), there is a factor \gamma. This parameter is setted to prevent the hinge loss to be 0. However, I haven't find this parameter in the code.
The 0 loss is quite common in deep learning and this phenomenon is usually called "overfit". In deep learning, people usually use dropout to prevent the loss from getting to zero too early.