Terence Parr personal blog

The Matrix Calculus You Need for Deep Learning

Most of us last saw calculus in school, but derivatives are a critical part of machine learning, particularly deep neural networks, which are trained by optimizing a loss function. This article is an attempt to explain all the matrix calculus you need in order to understand the training of deep neural networks. We…
Points
610
HN comments
167
Submissions
4
Cited by
5 commenters

AI & Machine LearningMath & Algorithms2018

On Hacker News

SubmittedTitle on HNPointsComments
Jun 29, 2018The Matrix Calculus You Need for Deep Learning by lxm61077
Nov 29, 2019Matrix Calculus for Deep Learning by yarapavan29647
Jul 30, 2023The matrix calculus you need for deep learning (2018) by mbustamanter22440
Mar 29, 2025The Matrix Calculus You Need for Deep Learning by Anon84673

Cited in comments

Linked from 5 Hacker News comments by 5 different people, from Jan 2020 to Jan 2026.

Most recent:

Search every comment that links here →

More from Terence Parr

All 4 posts →

Related posts from the same era