SOTAVerified

Efficient Per-Example Gradient Computations

2015-10-07Code Available2· sign in to hype

Ian Goodfellow

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

This technical report describes an efficient technique for computing the norm of the gradient of the loss function for a neural network with respect to its parameters. This gradient norm can be computed efficiently for every example.

Reproductions