Tag archive
Three approaches to computing derivatives, forward-mode AD, reverse-mode AD, and finite differences, each with different trade-offs for numerical computing and machine learning.
Dual numbers extend our number system with an infinitesimal epsilon where epsilon^2 = 0. Evaluating f(x + epsilon) yields f(x) + epsilon * f'(x)—the derivative emerges automatically from the algebra.
Calculus basics in the context of deep learning
Easy Math The Background This code aims to calculate three different math operations,...
This will be the 2020's web series about the foundation, architecture and deconstruction of mathemati...
I recently was doing the Mathematics for Machine Learning specialization on Coursera, which consists...
The Matrix Calculus You Need For Deep Learning (Notes from a paper by Te...