bigscience-workshop / bigscience-workshop/training_dynamics
Implement differentiable weight masks for modularity detection (from Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks)
Open
good first issue
- Dominant language
- No language data
- Stars
- 5
- Forks
- 4
- PR merge metrics
- No merged PRs in 30d
Description
Using [Csordás et al 2021](https://arxiv.org/abs/2010.02066) as a guide, implement differentiable weight masks to be used to detect modular substructures
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.