Differential Equations for Continuous-Time Deep Learning
This is an incremental survey targeting readers familiar with differential equations to explore their role in machine learning.
The paper introduces and surveys continuous-time deep learning approaches based on neural ordinary differential equations (neural ODEs), aiming to provide new insights into deep learning and a foundation for more efficient algorithms through examples from machine learning and applied mathematics.
This short, self-contained article seeks to introduce and survey continuous-time deep learning approaches that are based on neural ordinary differential equations (neural ODEs). It primarily targets readers familiar with ordinary and partial differential equations and their analysis who are curious to see their role in machine learning. Using three examples from machine learning and applied mathematics, we will see how neural ODEs can provide new insights into deep learning and a foundation for more efficient algorithms.