AI & ML Engineering · Unit 9 · Deep Learning
Deep Learning
Neural networks from the first neuron to a trained image model, in PyTorch.
- 9.1Video
Neural Networks
Neurons, layers, activation functions and the forward pass.
- 9.2Video
Backpropagation
How a network computes gradients and updates its weights.
- 9.3Video
PyTorch and the Training Loop
Tensors, autograd, data loaders, and the loop of batches, losses, optimisers and epochs.
- 9.4Video
Regularisation
Dropout, weight decay, batch normalisation and early stopping.
- 9.5Video
Convolutional Neural Networks
Convolutions, pooling and classic architectures for images.
- 9.6Video
Transfer Learning
Starting from a pretrained model instead of from zero.
Unit project
An image classifier trained on data you collected yourself, with its failure cases documented.
Paid learners get the full brief, submit it from their dashboard and have it reviewed. It goes in your portfolio.
Open every unit
Enrol once to open every unit, its videos and a reviewed project for your portfolio.