Fig. 12From: Reversible designs for extreme memory cost reduction of CNN trainingImpact of the numerical errors on the accuracy of (left) layer-wise invertible models and (right) hybrid architecture model. (Left): evolution of the accuracy with depth for a negative slope \(n=0.2\) with and without inverse reconstructions. Without reconstruction, the model accuracy benefits from depth. With inverse reconstructions, the model similarly benefits from depth as the number of layers grow from 3 to 7. For \(N>7\), however, the accuracy sharply decreases toward lower values due to numerical errors. (Right): our proposed hybrid architecture greatly stabilizes the numerical errors, which results in smaller effects of the depth and negative slope on accuracyBack to article page