LCA: Loss Change Allocation for Neural Network Training

Janice Lan, Rosanne Liu, Hattie Zhou, Jason Yosinski

Neural Information Processing Systems 

This rich view shows which parameters are responsible for decreasing or increasing the loss during training, orwhich parameters "help" or"hurt" the network'slearning, respectively.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found