Learning Curves for Analysis of Deep Networks

         Derek Hoiem 1 Tanmay Gupta 2 Zhizhong Li 1 Michal M. Shlapentokh-Rothman 1

             Abstract                 trapolate rather than evaluate and have typically required
                                  large-scale experiments that are outside the computational
   Learning curves model a classifier’s test error as a
                                  budgets of many research groups.
   function of the number of training samples. Prior
   ...