Create Neural Ordinary Differential Equations with 'tensorflow'

Provides a framework for the creation and use of Neural ordinary differential equations with the 'tensorflow' and 'keras' packages. The idea of Neural ordinary differential equations comes from Chen et al. (2018) , and presents a novel way of learning and solving differential systems.

tfNeuralODE

The goal of tfNeuralODE is to provide an easy framework surrounding the use of Neural Ordinary Differential Equations in R. This package does so by building on top of R Tensorflow, to help wth auto-differentiation and the construction of neural network models with Keras. Examples of this package in use can be found on the project website.

Installation

You can install the development version of tfNeuralODE like so:

devtools::install_github("https://github.com/semran9/tfNeuralODE.git")