matlab-deep-learning/constrained-deep-learning

Constrained deep learning is an advanced approach to training deep neural networks by incorporating domain-specific constraints into the learning process.

36
/ 100
Emerging

This project helps engineers, scientists, and AI verification specialists build deep learning models for safety-critical systems. By incorporating physical laws or logical rules, it produces neural networks that are guaranteed to behave predictably. Users input their domain-specific constraints and data to get models that adhere to essential properties like monotonicity or boundedness, ensuring reliable performance.

No commits in the last 6 months.

Use this if you need to build deep learning models for applications where predictable behavior and verifiable safety guarantees are absolutely essential, such as in aerospace, medical devices, or autonomous systems.

Not ideal if your primary goal is rapid prototyping or if your application doesn't require strict adherence to domain-specific constraints or formal verification.

AI verification safety-critical systems aerospace engineering predictive maintenance battery management
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

70

Forks

5

Language

MATLAB

License

Last pushed

Apr 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/matlab-deep-learning/constrained-deep-learning"

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