RobertCsordas / modules

The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.

Date Created 2020-07-12 (4 years ago)

Commits 24 (last one 3 years ago)

Stargazers 46 (0 this week)

Watchers 0 (0 this week)

Forks 9

License bsd-3-clause

Ranking

RepositoryStats indexes 584,777 repositories, of these RobertCsordas/modules is ranked #483,493 (17th percentile) for total stargazers, and #581,264 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #92,820/116,437.

RobertCsordas/modules is also tagged with popular topics, for these it's ranked: deep-learning (#7,252/8398), machine-learning (#6,896/7935), pytorch (#5,106/5951), transformers (#684/829), paper (#394/436)

Other Information

RobertCsordas/modules has 4 open pull requests on Github, 0 pull requests have been merged over the lifetime of the repository.

All Topics

rnn paper pytorch modularity transformers deep-learning generalization weight-sharing machine-learning

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

0 commits on the default branch (master) since jan '22

No recent commits to this repository

Yearly Commits

Commits to the default branch (master) per year

Issue History

Languages

The primary language is Python but there's also others...

updated: 2024-08-01 @ 01:10am, id: 279082703 / R_kgDOEKJ2zw