Perceptrons: The Origins of Trainable Neural Networks 🤖

Neural networks have become powerful tools for teaching computers to learn. But how did we train the first neural networks? In this video, we explore the first neural network that had the capacity to learn: the perceptron, developed by Frank Rosenblatt in 1957. We explore how the perceptron works and how it's able to learn from data, and we look at how Rosenblatt's perceptron compares to modern perceptrons.

This is Part 3 of Teaching Computers to Learn, a series on the development of artificial intelligence. Watch the whole series at https://www.youtube.com/watch?v=HzLom8rk2zo&list=PLZErML25eQ-NH9pF6zfcrB06tFT4qFeAJ.

***

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

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

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

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

Email me at brian@spanningtree.me to suggest a future topic.