Neural ordinary differential equations

RTQ Chen, Y Rubanova… - Advances in neural …, 2018 - proceedings.neurips.cc
We introduce a new family of deep neural network models. Instead of specifying a discrete
sequence of hidden layers, we parameterize the derivative of the hidden state using a …

Scalable gradients for stochastic differential equations

X Li, TKL Wong, RTQ Chen… - … Conference on Artificial …, 2020 - proceedings.mlr.press
The adjoint sensitivity method scalably computes gradients of solutions to ordinary
differential equations. We generalize this method to stochastic differential equations …

Neural jump stochastic differential equations

J Jia, AR Benson - Advances in Neural Information …, 2019 - proceedings.neurips.cc
Many time series are effectively generated by a combination of deterministic continuous
flows along with discrete jumps sparked by stochastic events. However, we usually do not …

Considering discrepancy when calibrating a mechanistic electrophysiology model

CL Lei, S Ghosh, DG Whittaker… - … of the Royal …, 2020 - royalsocietypublishing.org
Uncertainty quantification (UQ) is a vital step in using mathematical models and simulations
to take decisions. The field of cardiac simulation has begun to explore and adopt UQ …

Neural stochastic differential equations: Deep latent gaussian models in the diffusion limit

B Tzen, M Raginsky - ar** review of opportunities and challenges
Y Ye, A Pandey, C Bawden, DM Sumsuzzman… - Nature …, 2025 - nature.com
Integrating prior epidemiological knowledge embedded within mechanistic models with the
data-mining capabilities of artificial intelligence (AI) offers transformative potential for …

Infinitely deep bayesian neural networks with stochastic differential equations

W Xu, RTQ Chen, X Li… - … Conference on Artificial …, 2022 - proceedings.mlr.press
We perform scalable approximate inference in continuous-depth Bayesian neural networks.
In this model class, uncertainty about separate weights in each layer gives hidden units that …

Neural jump ordinary differential equations: Consistent continuous-time prediction and filtering

C Herrera, F Krach, J Teichmann - arxiv preprint arxiv:2006.04727, 2020 - arxiv.org
Combinations of neural ODEs with recurrent neural networks (RNN), like GRU-ODE-Bayes
or ODE-RNN are well suited to model irregularly observed time series. While those models …