2025年04月01日 星期二 登录 EN

学术活动
Expressivity in Neural Networks: Theory and Applications
首页 - 学术活动
报告人:
Juncai He, Assistant Professor, Yau Mathematical Sciences Center, Tsinghua University
邀请人:
Shuo Zhang, Associate Professor
题目:
Expressivity in Neural Networks: Theory and Applications
时间地点:
14:30-15:30 February 27(Thursday), Z311
摘要:

I will present recent results on the expressivity of neural networks and its applications. First, we will recall the connections between linear finite elements and ReLU deep neural networks (DNNs), as well as between spectral methods and ReLUk$^k$ DNNs. Next, we will share our latest findings on whether DNNs can precisely recover continuous piecewise polynomials of arbitrary order on any simplicial mesh in any dimension. Furthermore, we will discuss a specific result on the optimal expressivity of ReLU DNNs and its applications, incorporating the Kolmogorov-Arnold representation theorem. Finally, I will conclude with a remark on studying convolutional neural networks from an expressivity perspective.