Module 1 · Introduction to Deep Learning & Neural Networks
Neural Network Foundations: lessons
What a neural network actually computes, why the nonlinearity is the whole trick, and how the weights learn.
4 lessons · 1h 20m · 1 free to read now
What this module teaches, what it asks of you first and how you practise it are on its syllabus page.
Open the syllabusA neuron is a weighted sum plus one bending function. Stack a few and a straight line becomes whatever boundary you need.
Activation Functions: ReLU, GELU and Friends
15 minWhy the sigmoid has all but vanished from hidden layers, and what replaced it.
Included with the track Simulation insideBackpropagation Without the Fear
20 minThe chain rule, computation graphs, and why one backward pass is enough for millions of weights.
Included with the track Simulation insideYour First Training Loop in PyTorch
25 minFrom tensors to a trained model: forward, loss, backward, step — and how to read the curves.
Included with the track Simulation inside