In this paper, we develop a new neural network family based on power series expansion, which is proved to achieve a better approximation accuracy comparing to existing neural networks. This new set of neural networks can improve the expressive power while preserving comparable computational cost by increasing the degree of the network instead of increasing the depth or width. Numerical results have shown the advantage of this new neural network.

中文翻译：

---

幂级数展开神经网络

在本文中，我们基于幂级数展开开发了一个新的神经网络家族，与现有的神经网络相比，它被证明具有更好的逼近精度。通过增加网络的程度而不是增加深度或宽度，这种新的神经网络集可以提高表达能力，同时保留相当的计算成本。数值结果表明了这种新神经网络的优势。