Lagrangian Gaussian Processes use discrete Euler-Lagrange equations to condition GPs, preserving geometric structure for stable dynamics learning from sparse position snapshots without velocities.
Dissipative Hamiltonian Neural Networks: Learning Dissipative and Conservative Dynamics Separately
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
NEXUS introduces a graph-based neural energy-field model that derives forces from scalar energy and dissipation terms to achieve physically consistent contact-rich 3D dynamics.
A new framework infers multiscale stochastic neuromechanical models from neural and locomotion recordings to accurately describe and predict C. elegans dynamics for potential optogenetic control.
ASRNNs recover Hamiltonian dynamics and symbolic equations from trajectories with only two irregularly spaced noisy points by preserving symplectic structure without derivative estimation.
Metriplector treats neural computation as coupled metriplectic field dynamics whose stress-energy tensor readout achieves competitive results on vision, control, Sudoku, language modeling, and pathfinding with small parameter counts.
Hamiltonian Graph Networks achieve 150-600x faster training via random feature parameter construction while retaining comparable accuracy and physical invariances on N-body systems up to 10,000 particles.
citing papers explorer
-
Structure-Preserving Gaussian Processes Via Discrete Euler-Lagrange Equations
Lagrangian Gaussian Processes use discrete Euler-Lagrange equations to condition GPs, preserving geometric structure for stable dynamics learning from sparse position snapshots without velocities.
-
NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics
NEXUS introduces a graph-based neural energy-field model that derives forces from scalar energy and dissipation terms to achieve physically consistent contact-rich 3D dynamics.
-
Predicting and controlling nonlinear neuro-mechanical locomotion dynamics
A new framework infers multiscale stochastic neuromechanical models from neural and locomotion recordings to accurately describe and predict C. elegans dynamics for potential optogenetic control.
-
Machine Learning Hamiltonian Dynamical Systems with Sparse and Noisy Data
ASRNNs recover Hamiltonian dynamics and symbolic equations from trajectories with only two irregularly spaced noisy points by preserving symplectic structure without derivative estimation.
-
Metriplector: From Field Theory to Neural Architecture
Metriplector treats neural computation as coupled metriplectic field dynamics whose stress-energy tensor readout achieves competitive results on vision, control, Sudoku, language modeling, and pathfinding with small parameter counts.
-
Rapid training of Hamiltonian graph networks using random features
Hamiltonian Graph Networks achieve 150-600x faster training via random feature parameter construction while retaining comparable accuracy and physical invariances on N-body systems up to 10,000 particles.