REVIEW 2 cited by
What is an equivariant neural network?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We explain equivariant neural networks, a notion underlying breakthroughs in machine learning from deep convolutional neural networks for computer vision to AlphaFold 2 for protein structure prediction, without assuming knowledge of equivariance or neural networks. The basic mathematical ideas are simple but are often obscured by engineering complications that come with practical realizations. We extract and focus on the mathematical aspects, and limit ourselves to a cursory treatment of the engineering issues at the end.
Forward citations
Cited by 2 Pith papers
-
Multi-objective optimization and quantum hybridization of equivariant deep learning interatomic potentials
Inserting a quantum depth-infused layer into Allegro gives the best force accuracy on a copper-lithium dataset, about 13% better than a classical MLP variant, but not on other datasets.
-
Supervised Machine Learning Methods with Uncertainty Quantification for Exoplanet Atmospheric Retrievals from Transmission Spectroscopy
On a synthetic JWST/Ariel-style spectral database, XGBoost and SVM with per-spectrum normalization and log-abundance targets outperform random forests and other classical regressors for exoplanet atmospheric retrievals.
Discussion (0). Sign in to comment.