Phase 0: ML foundations
Learn how machines learn, from scratch, in plain numbers. Every model in the later phases is trained with the same few ideas: a loss that says how wrong it is, gradient descent that nudges the weights, a small network that turns inputs into outputs, and backpropagation that tells each weight how to change. This optional warm-up teaches them with tiny examples you can check by hand, so nothing later feels like magic.
After this phase you can
- Explain AI, machine learning and deep learning, and split data into train, validation and test sets
- Compute a loss and take gradient-descent steps by hand
- Follow a forward and backward pass through a tiny neural network and spot overfitting
Before you start: Basic Python and school maths. Skip this phase if you already know gradient descent and backpropagation.
Lessons in this phase
- AI, Machine Learning and Deep Learning Beginner · 8 min
AI is the big goal of making machines act intelligently, machine learning is the way of reaching it by learning from examples instead of writing rules.
- Loss and Gradient Descent Beginner · 9 min
A loss is a single number that says how wrong the model is, and gradient descent is the method that nudges the model's parameters downhill on that number, a small step at a time.
- Neurons and Forward Propagation Beginner · 9 min
A neuron multiplies its inputs by weights, adds them up with a bias, and passes the total through an activation function; forward propagation is just doing that layer after layer to get a prediction.
- Backpropagation Intermediate · 11 min
Backpropagation uses the chain rule to work out, in one backward sweep through the network, how much each weight contributed to the loss, so gradient descent knows how to change every weight.
- Overfitting and Regularization Intermediate · 10 min
Overfitting is when a model memorises the quirks and noise of its training data and so does worse on new data; regularization is any trick that makes memorising harder, such as an L2 penalty, early stopping.