Methods › Graphs › Graph Models › Symbolic Deep Learning
Symbolic Deep Learning
Introduced by Miles Cranmer et al. in Discovering Symbolic Models from Deep Learning with Inductive Biases
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
This is a general approach to convert a neural network into an analytic equation. The technique works as follows:
- Encourage sparse latent representations
- Apply symbolic regression to approximate the transformations between in/latent/out layers
- Compose the symbolic expressions.
In the paper, we show that we find the correct known equations, including force laws and Hamiltonians, can be extracted from the neural network. We then apply our method to a non-trivial cosmology example-a detailed dark matter simulation-and discover a new analytic formula which can predict the concentration of dark matter from the mass distribution of nearby cosmic structures. The symbolic expressions extracted from the GNN using our technique also generalized to out-of-distribution data better than the GNN itself. Our approach offers alternative directions for interpreting neural networks and discovering novel physical principles from the representations they learn.
Papers archive 2025-07-28
1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Discovering Symbolic Models from Deep Learning with Inductive Biases 19 Jun 2020 · 3 repositories · arXiv:2006.11287Syntology ran 0 of 6 samples · 6 unverified
Tasks archive 2025-07-28
2 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Deep Learning | 1 |
| Symbolic Regression | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections