Shamar/ANN-decompiler

"AI" demystified: a decompiler

29
/ 100
Experimental

This tool helps demystify how 'AI' models work by showing you the original training data they were built upon. It takes a trained statistical model, often called an 'artificial neural network', and works backward to reconstruct the dataset that was used to program it. This is for anyone who uses or relies on AI systems and wants to understand their origins and potential biases.

No commits in the last 6 months.

Use this if you need to verify the source data or understand the statistical programming behind a trained 'AI' model.

Not ideal if you are looking for a tool to build or train new AI models, as this focuses on deconstruction rather than construction.

AI-auditing data-provenance model-analysis statistical-programming
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

24

Forks

2

Language

Python

License

Last pushed

Sep 02, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Shamar/ANN-decompiler"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.