google-research/reverse-engineering-neural-networks
A collection of tools for reverse engineering neural networks.
This collection of tools helps machine learning researchers understand how complex neural networks, especially recurrent ones, make decisions. It takes a trained neural network and applies analysis techniques to reveal its internal workings, providing insights into why and how the network arrived at its outputs. Researchers in AI interpretability or theoretical neuroscience would find this useful.
168 stars. No commits in the last 6 months.
Use this if you are an AI researcher or theoretician aiming to deconstruct and understand the internal dynamics of trained recurrent neural networks.
Not ideal if you are looking for tools to simply train neural networks or to apply them for practical, real-world prediction tasks.
Stars
168
Forks
29
Language
Jupyter Notebook
License
Apache-2.0
Last pushed
Sep 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google-research/reverse-engineering-neural-networks"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...