Search Results for author: Zheng-an Chen

Found 1 papers, 0 papers with code

On the dynamics of three-layer neural networks: initial condensation

no code implementations25 Feb 2024 Zheng-an Chen, Tao Luo

Empirical and theoretical works show that the input weights of two-layer neural networks, when initialized with small values, converge towards isolated orientations.

Cannot find the paper you are looking for? You can Submit a new open access paper.