The Surprising Simplicity of the Early-Time Learning
Dynamics of Neural Networks
Wei Hu Lechao Xiao Ben Adlam Jeffrey Pennington§
Abstract
Modern neural networks are often regarded as complex black-box functions whose
behavior is difficult to understand owing to their nonlinear dependence on the data
and the nonconvexity in their loss landscapes. In this work, we show that these
common perceptions can be completely f ...


雷达卡


京公网安备 11010802022788号







