Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/google-research/reverse-engineering-neural-networks

A collection of tools for reverse engineering neural networks.

https://github.com/google-research/reverse-engineering-neural-networks

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.6%) to scientific vocabulary

Keywords

deep-learning interpretability machine-learning
Last synced: 4 months ago · JSON representation

Repository

A collection of tools for reverse engineering neural networks.

Basic Info
  • Host: GitHub
  • Owner: google-research
  • License: apache-2.0
  • Language: Jupyter Notebook
  • Default Branch: master
  • Homepage:
  • Size: 2.79 MB
Statistics
  • Stars: 158
  • Watchers: 12
  • Forks: 28
  • Open Issues: 8
  • Releases: 10
Topics
deep-learning interpretability machine-learning
Created over 5 years ago · Last pushed over 2 years ago
Metadata Files
Readme License

README.md

Reverse Engineering Neural Networks (RENN)

build

renn is a collection of python utilities for reverse engineering neural networks. The goal of the package is to be a shared repository of code, notebooks, and ideas for how to crack open the black box of neural networks to understand what they are doing and how they work. Our focus is on research applications.

Currently, the package focuses on understanding recurrent neural networks (RNNs). We provide code to build and train common RNN architectures, as well as code for understanding the dynamics of trained RNNs through dynamical systems analyses. The core tools for this involve finding and analyzing approximate fixed points of the dynamics of a trained RNN.

All of renn uses the JAX machine learning library for building neural networks and for automatic differentiation. We assume some basic familiarity with JAX in the documentation.

See the documentation for more information.

Authors: - Niru Maheswaranathan (nirum@google.com) - Vinay Ramasesh (ramasesh@google.com)

Owner

  • Name: Google Research
  • Login: google-research
  • Kind: organization
  • Location: Earth

GitHub Events

Total
  • Watch event: 10
  • Fork event: 4
Last Year
  • Watch event: 10
  • Fork event: 4

Committers

Last synced: 5 months ago

All Time
  • Total Commits: 115
  • Total Committers: 5
  • Avg Commits per committer: 23.0
  • Development Distribution Score (DDS): 0.635
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Vinay Ramasesh r****h@g****m 42
Niru Maheswaranathan n****m@g****m 40
Niru Maheswaranathan n****u@f****m 23
ramasesh v****0@g****m 9
Niru Maheswaranathan n****u@h****m 1
Committer Domains (Top 20 + Academic)
google.com: 2 hey.com: 1 fastmail.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 18
  • Total pull requests: 37
  • Average time to close issues: 16 days
  • Average time to close pull requests: 16 days
  • Total issue authors: 3
  • Total pull request authors: 4
  • Average comments per issue: 0.28
  • Average comments per pull request: 0.35
  • Merged pull requests: 32
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • nirum (14)
  • ramasesh (3)
  • luantunez (1)
Pull Request Authors
  • ramasesh (22)
  • nirum (13)
  • caoyuan (1)
Top Labels
Issue Labels
enhancement (5) testing (3) refactor (2) documentation (2) bug (2)
Pull Request Labels
enhancement (3)

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 43 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 2
  • Total versions: 9
  • Total maintainers: 1
pypi.org: renn

Research tools for Reverse Engineering Neural Networks (RENN).

  • Versions: 9
  • Dependent Packages: 0
  • Dependent Repositories: 2
  • Downloads: 43 Last month
Rankings
Forks count: 6.7%
Stargazers count: 6.7%
Dependent packages count: 10.1%
Dependent repos count: 11.6%
Average: 19.4%
Downloads: 61.8%
Maintainers (1)
nirum
Last synced: 5 months ago

Dependencies

docs/requirements.txt pypi
  • nbsphinx *
  • renn *
  • sphinx *
  • sphinx_rtd_theme *
requirements.txt pypi
  • jax *
  • jaxlib *
  • msgpack *
  • numpy *
  • sklearn *
  • tensorflow *
  • tensorflow-text *
  • tfds-nightly *
  • toolz *
  • tqdm *
setup.py pypi
  • jax *
  • jaxlib *
  • msgpack *
  • numpy *
  • sklearn *
  • tensorflow *
  • tensorflow-text *
  • tfds-nightly *
  • tqdm *
.github/workflows/continuous-integration.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
  • codecov/codecov-action v1.0.12 composite