Build Neural Networks from Scratch in Python 🧠

We'll learn the theory of neural networks, then use Python and NumPy to implement a complete multi-layer neural network. We'll cover the forward pass, loss functions, the backward pass (backpropagation and gradient descent), and the training loop. At the end, we'll use our neural network to predict the weather.

You can find the text version of this lesson here - https://github.com/VikParuchuri/zero_to_gpt/blob/master/explanations/dense.ipynb

And the complete lesson list for the zero to gpt series here - https://github.com/VikParuchuri/zero_to_gpt

Chapters

00:00:00 Neural network introduction
00:10:05 Activation functions
00:12:10 Multiple layers
00:15:18 Multiple hidden units
00:23:52 The forward pass
00:32:46 The backward pass
00:48:08 Layer 1 gradients
00:56:24 Network training algorithm
01:00:13 Full network implementation
01:06:44 Training loop

This video is part of our new course, Zero to GPT - a guide to building your own GPT model from scratch. By taking this course, you'll learn deep learning skills from the ground up. Even if you're a complete beginner, you can start with the prerequisites we offer at Dataquest to get you started.

If you're dreaming of building deep learning models, this course is for you.

Best of all, you can access the course for free while it's still in beta!

Sign up today!
https://bit.ly/4016NfK