Parsimonious neural networks learn interpretable physical laws
Abstract Machine learning is playing an increasing role in the physical sciences and significant progress has been made towards embedding domain knowledge into models. Less explored is its use to discover interpretable physical laws from data. We propose parsimonious neural networks (PNNs) that comb...
Enregistré dans:
Auteurs principaux: | Saaketh Desai, Alejandro Strachan |
---|---|
Format: | article |
Langue: | EN |
Publié: |
Nature Portfolio
2021
|
Sujets: | |
Accès en ligne: | https://doaj.org/article/7b24e1e0a740421f8df33a3f6cfc3068 |
Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
-
Neural network reactive force field for C, H, N, and O systems
par: Pilsun Yoo, et autres
Publié: (2021) -
Near-surface real-time seismic imaging using parsimonious interferometry
par: Sherif M. Hanafy, et autres
Publié: (2021) -
Using genes as characters and a parsimony analysis to explore the phylogenetic position of turtles.
par: Bin Lu, et autres
Publié: (2013) -
Rec-DCM-Eigen: reconstructing a less parsimonious but more accurate tree in shorter time.
par: Seunghwa Kang, et autres
Publié: (2011) -
Off-the-shelf deep learning is not enough, and requires parsimony, Bayesianity, and causality
par: Rama K. Vasudevan, et autres
Publié: (2021)