Learning Neural Event Functions for Ordinary Differential Equations
arXiv:2011.03902
Abstract
The existing Neural ODE formulation relies on an explicit knowledge of the termination time. We extend Neural ODEs to implicitly defined termination criteria modeled by neural event functions, which can be chained together and differentiated through. Neural Event ODEs are capable of modeling discrete and instantaneous changes in a continuous-time system, without prior knowledge of when these changes should occur or how many such changes should exist. We test our approach in modeling hybrid discrete- and continuous- systems such as switching dynamical systems and collision in multi-body systems, and we propose simulation-based training of point processes with applications in discrete control.
References in corpus (12)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- The NumPy array: a structure for efficient numerical computation
- Latent ODEs for Irregularly-Sampled Time Series
- Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control
- Generalized Inner Loop Meta-Learning
- ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
- Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
- Recurrent switching linear dynamical systems
- CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
- Neural Networks with Cheap Differential Operators
- MALI: A memory efficient and reverse accurate integrator for Neural ODEs
- Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory
Cited by in corpus (9)
- Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
- Neural Controlled Differential Equations for Online Prediction Tasks
- Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions
- MonoForce: Self-supervised Learning of Physics-informed Model for Predicting Robot-terrain Interaction
- Policy Analysis using Synthetic Controls in Continuous-Time
- Piecewise-constant Neural ODEs
- Enhancing Dynamical System Modeling through Interpretable Machine Learning Augmentations: A Case Study in Cathodic Electrophoretic Deposition
- STRODE: Stochastic Boundary Ordinary Differential Equation
- Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics