Search Results for author:
Found 4 papers, 3 papers with code
Parallelizing non-linear sequential models over the sequence length
Sequential models, such as Recurrent Neural Networks and Neural Ordinary Differential Equations, have long suffered from slow training due to their inherent sequential nature.
Ranked #5 on
Time Series Classification
on EigenWorms
Constants of motion network
The beauty of physics is that there is usually a conserved quantity in an always-changing system, known as the constant of motion.
Unifying physical systems' inductive biases in neural ODE using dynamics constraints
There have been a significant number of works in the past few years aimed at predicting the trajectory of motion of dynamical systems using neural networks while adhering to the law of conservation of energy.
Reducing the Long Tail Losses in Scientific Emulations with Active Learning
Deep-learning-based models are increasingly used to emulate scientific simulations to accelerate scientific research.
