tensorflow / tensorflow/probability
DenseFlipout without a bias term
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
Hi all,
I'm still quite new to Bayesian inference and TF-Probability, but I'd like to know how I could use the DenseFlipout without a bias term? In my application I know (or rather, I need) the bias to be vanishing, how could I enforce this (as similar to the use_bias flag in Dense or DenseVariational)?
Cheers
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by examining the DenseFlipout and DenseVariational entry points named in the issue, then compare how the existing bias option is exposed. Determine how DenseFlipout should represent a vanishing bias and define completion as being able to use it without a bias term, with coverage for the resulting behavior.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100