DiffEqML/torchdyn

A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods

45
/ 100
Emerging

This library helps machine learning researchers and practitioners build advanced deep learning models that incorporate the principles of differential equations and dynamical systems. You provide your existing PyTorch neural network modules, and the library converts them into continuous, trainable models like Neural ODEs, which can then be used for tasks like predicting complex system behavior or processing unique data types. It's designed for those pushing the boundaries of traditional deep learning architectures.

1,555 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or advanced practitioner who needs to design deep learning models capable of understanding and predicting continuous processes, such as those found in physics, control systems, or advanced signal processing.

Not ideal if you are looking for off-the-shelf solutions for standard classification or regression problems that can be solved with traditional neural network architectures.

numerical deep learning dynamical systems modeling scientific machine learning continuous neural networks physics-informed AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

1,555

Forks

133

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

May 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DiffEqML/torchdyn"

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