Efficient Per-Example Gradient Computations

Ian Goodfellow

Research

Artificial Intelligence And Data Science PDF Available Non-peer-reviewed Preprint

Efficient Per-Example Gradient Computations

Ian Goodfellow · Published 2015-10-07

Expertini /
Research /
Artificial Intelligence And Data Science /
Efficient Per-Example Gradient Computations

📄 Download PDF 🔖 Bookmark Paper

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.

Keywords

Artificial Intelligence & Data Science

📄 Full Paper Available as PDF

This paper is available as a downloadable PDF.

📄 Download PDF

Comments (0)

No comments yet. Be the first to comment.

Paper Details

Authors Ian Goodfellow
Published 2015-10-07
Category Artificial Intelligence And Data Science
Status Non-peer-reviewed Preprint
Language English
Word Count 37

Efficient Per-Example Gradient Computations

Abstract

Keywords

✨ AI Plain-English Summary

Comments (0)

Related Papers

An Efficient Algorithm for Computing Interventional Distributions in ...

Sparse matrix-variate Gaussian process blockmodels for network modeling

Hierarchical Maximum Margin Learning for Multi-Class Classification

Tightening MRF Relaxations with Planar Subproblems