tensorflow / tensorflow/probability

DenseFlipOut layer

Open
#88 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

good first issue layers
Dominant language
Jupyter Notebook
Stars
4.4k
Forks
1.1k
PR merge metrics
No merged PRs in 30d

Description

I am using the DenseFlipOut layer, I see that it has a mean_normal distribution over the weights and the biases by default, but I was wondering how these distributions are modified during training in comparison to regular networks with a Dense layer?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the DenseFlipOut layer implementation and comparing its training behavior with the regular Dense layer. Clarify how the mean_normal weight and bias distributions are modified during training, then document the comparison in terms that answer the reporter’s question.

Written by the indexing model from the issue text.

Assessment

Tech stack
tensorflow
Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.