Tilting the playing field: Dynamical loss functions for machine learning
Miguel Ruiz-Garcia 1 2 Ge Zhang 1 Samuel S. Schoenholz 3 Andrea J. Liu 1
Abstract tion scale (Glorot & Bengio, 2010; Xiao et al., 2018) or
learning rate schedule (He et al., 2016); the neural network
We show that learning can be improved by us- architecture itself (Zoph & Le, 2016); the types of data aug-
ing loss functions that evolve ...


雷达卡




京公网安备 11010802022788号







