by llSourcell

This is the code for the "Make a Neural Network" - Intro to Deep Learning #2 by Siraj Raval on Youtu...

195 Stars 213 Forks Last release: Not found 5 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:


This is the code for the "Make a Neural Network" - Intro to Deep Learning #2 by Siraj Raval on Youtube


This is the code for this video by Siraj Raval on Youtube. This is a simple single layer feedforward neural network (perceptron). We use binary digits as our inputs and expect binary digits as our outputs. We'll use backpropagation via gradient descent to train our network and make our prediction as accurate as possible.


None! Just numpy.



in terminal to see it train, then predict.


The challenge for this video is to create a 3 layer feedforward neural network using only numpy as your dependency. By doing this, you'll understand exactly how backpropagation works and develop an intuitive understanding of neural networks, which will be useful for more the more complex nets we build in the future. Backpropagation usually involves recursively taking derivatives, but in our 1 layer demo there was no recursion so was a trivial case of backpropagation. In this challenge, there will be. Use a small binary dataset, you can define one programmatically like in this example.

Bonus -- use a larger, more interesting dataset


The credits for this code go to Milo Harper. I've merely created a wrapper to get people started.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.