JonathanCrabbe/Simplex
This repository contains the implementation of SimplEx, a method to explain the latent representations of black-box models with the help of a corpus of examples. For more details, please read our NeurIPS 2021 paper: 'Explaining Latent Representations with a Corpus of Examples'.
This tool helps machine learning engineers and researchers understand why a complex 'black box' AI model makes a certain prediction by finding the most similar examples from a dataset. You input your opaque AI model and a collection of examples it has processed, and it outputs a weighted list of training examples that best explain the model's internal reasoning for a specific prediction.
No commits in the last 6 months.
Use this if you need to interpret the internal workings of black-box AI models, especially for critical applications where understanding predictions is paramount.
Not ideal if your AI models are already transparent and easily interpretable, or if you only need overall model insights rather than example-specific explanations.
Stars
24
Forks
8
Language
Python
License
Apache-2.0
Last pushed
Jan 31, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JonathanCrabbe/Simplex"
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...