lapalap/invert

Official GitHub for the paper "Labeling Neural Representations with Inverse Recognition"

/ 100

Experimental

This project helps machine learning researchers and practitioners understand what concepts their deep neural networks have learned. You input the activations from a trained neural network, and it outputs human-understandable labels describing what each part of the network (e.g., a neuron or feature) is responding to. This helps anyone working with neural networks to interpret their models.

Use this if you need to understand the internal workings of a deep neural network and map its complex representations to concepts you can comprehend.

Not ideal if you are looking for global model explanations that don't focus on individual neural representations or require extensive segmentation masks.

AI explainability neural network interpretation deep learning analysis model understanding machine learning research

No License No Package No Dependents

Maintenance 6 / 25

Adoption 5 / 25

Maturity 8 / 25

Community 7 / 25

How are scores calculated?

Stars

Forks

Language

Jupyter Notebook

License

—

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...

Explore ML Frameworks

All categories Trending ML Framework directory Insights