A residual network may be regarded as a discretization of an ordinary differential equation
(ODE) which, in the limit of time discretization, defines a continuous-depth network. Although
important steps have been taken to realize the advantages of such continuous formulations,
most current techniques assume identical layers. Indeed, existing works throw into relief the
myriad difficulties of learning an infinite-dimensional parameter in a continuous-depth neural
network. To this end, we introduce a shooting formulation which shifts the perspective from …

A Shooting Formulation of Deep Learning — Paris-Lodron-University Salzburg … A
Shooting Formulation of Deep Learning … Machine learning …