3 papers
cs.LG2026
Why Shallow Neural Networks Learn Sinusoidal Components First: An Orthogonal Polynomial Dynamics Framework
Yanyang Xiao
Neural networks often learn low-frequency components before high-frequency ones --- a phenomenon called spectral bias or termed F-principle. Many numerical studies have demonstrate…
cs.GR2025
Efficient Computation of Voronoi Diagrams Using Point-in-Cell Tests
Yanyang Xiao, Juan Cao, Zhonggui Chen
Since the Voronoi diagram appears in many applications, the topic of improving its computational efficiency remains attractive. We propose a novel yet efficient method to compute V…
q-bio.NC2022
Principles for generation of reverberation
Yi Ren, Yanyang Xiao, Guo-Qiang Bi +1
In modern neuroscience, memory has been postulated to stored in neural circuits as sequential spike train and Reverberation is one of the specific example.Former research has made…