← Search

Zhiying Fang

1 accepted papers

2021

Towards Understanding the Spectral Bias of Deep Learning

IJCAI 2021poster

An intriguing phenomenon observed during training neural networks is the spectral bias, which states that neural networks are biased towards learning less complex functions. The priority of learning functions with low complexity might be at the core of explaining the generalization ability of neural…

Cited by 265SourcePDFScholar