Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent

Jaehoon Lee, Lechao Xiao, Samuel Schoenholz, Yasaman Bahri, Roman Novak, Jascha Sohl-Dickstein, Jeffrey Pennington

Neural Information Processing Systems 

However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found