Power Series Expansion Neural Network

Abstract

In this paper, we develop a new neural network family based on power series expansion, which is proved to achieve a better approximation accuracy in comparison with existing neural networks. This new set of neural networks embeds the power series expansion (PSE) into the neural network structure. Then it can improve the representation ability while preserving comparable computational cost by increasing the degree of PSE instead of increasing the depth or width. Both theoretical approximation and numerical results show the advantages of this new neural network.

arXiv comment12 pages, 1 figure

References in corpus (8)

• DeepXDE: A deep learning library for solving differential equations
• Deep Network Approximation for Smooth Functions
• ReLU Deep Neural Networks and Linear Finite Elements
• The Finite Neuron Method and Convergence Analysis
• Nonlinear Approximation via Compositions
• ReLU Deep Neural Networks from the Hierarchical Basis Perspective
• Machine learning based non-Newtonian fluid model with molecular fidelity
• A Weight Initialization Based on the Linear Product Structure for Neural Networks