Understanding the Universal Approximation Theorem in Neural Networks 🧠
Discover how neural networks can approximate any function with this essential theorem. Perfect for beginners and enthusiasts alike!
Michael Nielsen
81.8K views • Nov 3, 2017
About this video
For an introduction to artificial neural networks, see Chapter 1 of my
free online book: http://neuralnetworksanddeeplearning.com/chap1.html
A good series of videos on neural networks is by 3Blue1Brown. Start
here: https://www.youtube.com/watch?v=aircAruvnKk
This video just shows the (very simple!) basic idea of the proof. For the full proof of the universal approximation theorem, including caveats that didn't make it into this video, see Chapter 4 of my book:
http://neuralnetworksanddeeplearning.com/chap4.html
This video was made as part of a larger project, on media for mathematics: http://cognitivemedium.com/magic_paper/
free online book: http://neuralnetworksanddeeplearning.com/chap1.html
A good series of videos on neural networks is by 3Blue1Brown. Start
here: https://www.youtube.com/watch?v=aircAruvnKk
This video just shows the (very simple!) basic idea of the proof. For the full proof of the universal approximation theorem, including caveats that didn't make it into this video, see Chapter 4 of my book:
http://neuralnetworksanddeeplearning.com/chap4.html
This video was made as part of a larger project, on media for mathematics: http://cognitivemedium.com/magic_paper/
Video Information
Views
81.8K
Likes
2.2K
Duration
6:25
Published
Nov 3, 2017
User Reviews
4.7
(16)