Skip to content

Feature: L1, L2 Regularizers #20

Closed
@WuZhuoran

Description

@WuZhuoran
Contributor

We can implement Regularizer for each layer. The regularizers are applied on a per-layer basis. Here are 3 things that we can do:

  1. Regularizer Class.
  2. Layers class to use regularizer. (we can set a new parameter)
  3. Regularizer Documentation.
  4. Regularizer Test.

I will start a PR to solve 1 and 3. The rest part should be discussed before coding.

Activity

WuZhuoran

WuZhuoran commented on Jul 15, 2019

@WuZhuoran
ContributorAuthor

In order to avoid Keras or other package way of implementing this, we need to first discuss how to implement Regularizer in general. Then I will re commit everything.

ddbourgin

ddbourgin commented on Jul 25, 2020

@ddbourgin
Owner

Closing due to inactivity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

      Development

      Participants

      @ddbourgin@WuZhuoran

      Issue actions

        Feature: L1, L2 Regularizers · Issue #20 · ddbourgin/numpy-ml