72 citations · 96 across the 2 of their papers we have counts for
2 papers
cs.CV2017★ 72 cited
Reversible Architectures for Arbitrarily Deep Residual Neural Networks
Bo Chang, Lili Meng, Eldad Haber +3
Recently, deep residual networks have been successfully applied in many computer vision and natural language processing tasks, pushing the state-of-the-art performance with deeper…
cs.NE2017★ 24 cited
Learning across scales - A multiscale method for Convolution Neural Networks
Eldad Haber, Lars Ruthotto, Elliot Holtham +1
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…