An ode for ODE

As most of us already know about the paper being presented at NeurIPS this year, entitled Neural Ordinary Differential Equations, written by Ricky Chen, Yulia Rubanova, Jesse Bettencourt, and David Duvenaud from the University of Toronto , the future of machine learning models may change dramatically based on the findings of this paper .
Basically it talks about bringing continuity to a discrete methodology of the contemporary neural networking models , the main idea being those types of neural networks which are analogous to a discretized differential equation may use differential equation solvers to achieve a higher level of accuracy and efficiency .