Mathematical Origins of Machine Learning | Teaching Computers to Learn, Part 2

Many of the ideas that are central to artificial intelligence have their roots in ideas developed hundreds of years ago. In this video, we explore a few key mathematicians and their ideas — Carl Friedrich Gauss searching for a missing planet, Gottfried Wilhelm Leibniz studying functions and how they change, and Augustin-Louis Cauchy trying to optimize orbital models — and understand how their work laid the foundation for the techniques we use in machine learning today, through the development of the method of least squares, the chain rule, and the gradient descent algorithm.

This is Part 2 of Teaching Computers to Learn, a series on the development of artificial intelligence. See Part 1 at    • Teaching Computers to Learn, Part 1  .

***

Spanning Tree is an educational video series about computer science and mathematics. See more at https://spanningtree.me

You can support the Spanning Tree channel at https://ko-fi.com/spanningtree

To be notified when a new video is released, sign up for the Spanning Tree mailing list at https://spanningtree.substack.com/

Spanning Tree is created by Brian Yu. https://brianyu.me/

Email me at [email protected] to suggest a future topic.

0:00 A Missing Planet
1:37 Parameters
2:53 Method of Least Squares
6:04 Calculus
6:50 Chain Rule
9:51 Gradient Descent