Skip to content

Restricting attention weights to domain #43

@MichaelHopwood

Description

@MichaelHopwood

In my application, the attention weights are centering on locations which are indicative of a subset of the classes. Therefore, while the algorithm performs well on this subset, it sometimes misclassifies on the other classes because the attention weights cause the obvious differences to be considered "residual".

Is there a documented way of restricting the attention weights to a certain value or index domain to enforce constraints on its focus? This question makes me think of NLP problems where frameworks commonly pair ML methodologies with a set of predetermined rules (usually defined with spacy).

Any thoughts? Thanks in advance.

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