There is an analogy between the ResNet (Residual Network) architecture for deep neural networks and an Euler solver for an ODE. The transformation performed by each layer resembles an Euler step in solving an ODE. We consider the Heun Method, which involves a single predictor-corrector cycle, and complete the analogy, building a predictor-corrector variant of ResNet, which we call a HeunNet. Just as Heun's method is more accurate than Euler's, experiments show that HeunNet achieves high accuracy with low computational (both training and test) time compared to both vanilla recurrent neural networks and other ResNet variants.

翻译：深海神经网络的ResNet(Residual Net)架构与ODE的 Euler 求解器之间有一个类比。 每层的变换类似于解决 ODE 的Euler 步骤。 我们考虑Heun 方法,它涉及单一的预测器-纠正器周期,完成类比,建立一个ResNet的预测器-纠正器变体,我们称之为HeunNet。正如Heun的方法比Euler的方法更准确,实验显示HeunNet在与香草经常性神经网络和其他ResNet变体相比的低计算(培训和测试)时间下取得了很高的准确性。