Ceyron/trainax

Training methodologies for autoregressive neural operators/emulators in JAX.

21
/ 100
Experimental

This project helps scientists and engineers working with complex simulations or physical systems create faster, data-driven approximations. It takes in real or simulated time-dependent data (like sensor readings or simulation outputs) and uses it to train a neural network. The output is a highly optimized "neural emulator" that can predict how a system evolves over time much quicker than traditional simulators.

No commits in the last 6 months.

Use this if you need to rapidly predict the behavior of time-dependent physical systems or simulations without running computationally expensive full models.

Not ideal if you are looking for a general-purpose machine learning library or if your problem doesn't involve emulating time-dependent physical processes.

scientific-simulation physics-modeling predictive-modeling time-series-forecasting computational-science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

Python

License

MIT

Last pushed

Nov 05, 2024

Commits (30d)

0

Get this data via API

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

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