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.
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.
Stars
70
Forks
5
Language
MATLAB
License
—
Category
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.
Higher-rated alternatives
lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.