Piecewise-constant Neural ODEs

Understand

Neural networks are a popular tool for modeling sequential data but they generally do not treat time as a continuous variable.

• Neural ODEs represent an important exception: they parameterize the time derivative of a hidden state with a neural network and then integrate over arbitrary amounts of time.
• But these parameterizations, which have arbitrary curvature, can be hard to integrate and thus train and evaluate.
• In this paper, we propose making a piecewise-constant approximation to Neural ODEs to mitigate these issues.