Explore how neural networks learn by programming one from scratch in C#, then trying to teach it to recognize various squiggles and images.

Source code: https://github.com/SebLague/Neural-Network-Experiments
Demo: https://sebastian.itch.io/neural-network-experiment

If you want to help me create more videos (and get early access to new things), you can join my patreon here: https://www.patreon.com/SebastianLague

The data comes from:
Figures http://yann.lecun.com/exdb/mnist/
Fashion https://github.com/zalandoresearch/fashion-mnist
Doodles https://github.com/googlecreativelab/quickdraw-dataset
Cifar10 https://www.cs.toronto.edu/~kriz/cifar.html

Chapters
00:00 Presentation
2:39 The decision limit
3:49 Weight
5:42 Bias
6:45 Hidden layers
7:45 a.m. Network programming
9:57 Activation functions
12:42 p.m. Cost
15:07 Example of gradient descent
18:22 The cost landscape
7:55 p.m. Programming the slope descent
9:10 p.m. It’s learning! (slowly)
23:21 Calculation example
27:34 The chain rule
29h50 Some partial derivatives
33:14 Backpropagation
39:25 Number recognition
43:56 Drawing our own numbers
47:37 Fashion
48:25 Doodles
52:00 The final challenge

Music:
Cosmic waves – Michael FK
Amber – The Stolen Orchestra
Beyond the horizon – It looks like Sander
Air – Assaf Ayalon
Purest form – Looks like Sander
Listen wide open – Sounds like Sander
Universal Wonder – Moments
Roman P – Moments
All In Good Times – Shimmer
He will come back – The Stolen Orchestra
Border – Shimmering
New Moon – Cloudy Wave
Sunflower – Cody Martin
Inner peace – Moments
Pleased – Cody Martin
Just around the corner – Shimmer

Please take the opportunity to connect and share this video with your friends and family if you find it useful.