Abstract

We introduce a new method for speeding up the inference of deep neural networks. It is somewhat inspired by the reduced-order modeling techniques for dynamical systems. The cornerstone of the proposed method is the maximum volume algorithm. We demonstrate efficiency on neural networks pre-trained on different datasets. We show that in many practical cases it is possible to replace convolutional layers with much smaller fully-connected layers with a relatively small drop in accuracy.

中文翻译：

---

深度神经网络的降阶建模

摘要

我们介绍了一种加速深度神经网络推理的新方法。它的灵感来自于动态系统的降阶建模技术。所提出方法的基石是最大体积算法。我们展示了在不同数据集上预训练的神经网络的效率。我们表明，在许多实际情况下，可以用更小的全连接层替换卷积层，但精度下降相对较小。