Repository files navigation

Thisrepository is the official implementation ofDiscovering Symbolic Models from Deep Learning with Inductive Biases.

Miles Cranmer, Alvaro Sanchez-Gonzalez, Peter Battaglia, Rui Xu, Kyle Cranmer, David Spergel, Shirley Ho

Check out ourBlog,Paper,Video, andInteractive Demo.

For model:

• pytorch
• pytorch-geometric
• numpy

Symbolic regression:

• PySR, our new open-source Eureqa alternative

For simulations:

• jax (simple N-body simulations)
• quijote (Dark matter data; optional)
• tqdm
• matplotlib

To train an example model from the paper, try out thedemo.

Full model definitions are given inmodels.py. Data is generated fromsimulate.py.

We train on simulations produced by the following equations:giving us time series:

We recorded performance for each model:and also measured how well each model's messagescorrelated with a linear combination of forces:

Finally, we trained on a dark matter simulation and extracted the following equationsfrom the message function: