Neural Differential Equations were proposed in 2018 as a new family of Neural Network models that would incorporate black box ODE solvers as a component.
Neural Differential Equations (Chen et al. 2018) were a family of deep neural network models proposed in 2018 as the infintely continuous variant of a discrete recurrent neural network. One of the major applications of such type of models was in time series data. Time Series are often directly modeled in terms of differential equations. In this article, we will explore the literature thats developed since the introduction of Neural ODES in 2018.
Chen, Ricky T. Q., Yulia Rubanova, Jesse Bettencourt, and David K Duvenaud. 2018. “Neural Ordinary Differential Equations.” In Advances in Neural Information Processing Systems, edited by S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett. Vol. 31. Curran Associates, Inc. https://proceedings.neurips.cc/paper/2018/file/69386f6bb1dfed68692a24c8686939b9-Paper.pdf.
For attribution, please cite this work as
Chitlangia (2021, May 15). Resources: Neural Differential Equations. Retrieved from https://resources.sharadchitlang.ai/posts/2021-05-14-neural-differential-equations/
BibTeX citation
@misc{chitlangia2021neural,
author = {Chitlangia, Sharad},
title = {Resources: Neural Differential Equations},
url = {https://resources.sharadchitlang.ai/posts/2021-05-14-neural-differential-equations/},
year = {2021}
}