Interpretable machine learning in Physics

03/11/2022

∙

Adding interpretability to multivariate methods creates a powerful synergy for exploring complex physical systems with higher order correlations while bringing about a degree of clarity in the underlying dynamics of the system.

READ FULL TEXT

Interpretable machine learning in Physics

Interpretable machine learning models: a physics-based view

Learning Integrable Dynamics with Action-Angle Networks

Inferring Local Structure from Pairwise Correlations

Voronoi cell analysis: The shapes of particle systems

Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems

On Second Order Behaviour in Augmented Neural ODEs

A simple equivariant machine learning method for dynamics based on scalars

Interpretable machine learning in Physics

Related Research

Interpretable machine learning models: a physics-based view

Learning Integrable Dynamics with Action-Angle Networks

Inferring Local Structure from Pairwise Correlations

Voronoi cell analysis: The shapes of particle systems

Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems

On Second Order Behaviour in Augmented Neural ODEs

A simple equivariant machine learning method for dynamics based on scalars