The Math Behind the Adam Optimizer

Why is Adam the most popular optimizer in Deep Learning? Let’s understand it by diving into its math, and recreating the algorithm

Cristian Leo
Towards Data Science
16 min readJan 30, 2024

--

Image generated by DALLE-2

If you’ve clicked on this article, you’ve likely heard about Adam, a name that has gained notable recognition in many winning Kaggle competitions. It’s common to experiment with a few…

--

--

A Data Scientist with a passion about recreating all the popular machine learning algorithm from scratch.