15 citations · 15 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023★ 15 cited
Deep Network Approximation: Beyond ReLU to Diverse Activation Functions
Shijun Zhang, Jianfeng Lu, Hongkai Zhao
This paper explores the expressive power of deep neural networks for a diverse range of activation functions. An activation function set is defined to encompass the m…
cs.LG2023
On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network
Shijun Zhang, Jianfeng Lu, Hongkai Zhao
This paper explores the expressive power of deep neural networks through the framework of function compositions. We demonstrate that the repeated compositions of a single fixed-siz…