Skip to content

Where is the parameter \gamma #2

Description

@happynear

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.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions