# Learning across scales - A multiscale method for Convolution Neural Networks

6 Mar 2017Eldad HaberLars RuthottoElliot HolthamSeong-Hwan Jun

In this work we establish the relation between optimal control and training deep Convolution Neural Networks (CNNs). We show that the forward propagation in CNNs can be interpreted as a time-dependent nonlinear differential equation and learning as controlling the parameters of the differential equation such that the network approximates the data-label relation for given training data... (read more)

PDF Abstract