AI & ML Engineering · Unit 9 · Deep Learning

Deep Learning

Neural networks from the first neuron to a trained image model, in PyTorch.

  1. 9.1

    Neural Networks

    Neurons, layers, activation functions and the forward pass.

    Video
  2. 9.2

    Backpropagation

    How a network computes gradients and updates its weights.

    Video
  3. 9.3

    PyTorch and the Training Loop

    Tensors, autograd, data loaders, and the loop of batches, losses, optimisers and epochs.

    Video
  4. 9.4

    Regularisation

    Dropout, weight decay, batch normalisation and early stopping.

    Video
  5. 9.5

    Convolutional Neural Networks

    Convolutions, pooling and classic architectures for images.

    Video
  6. 9.6

    Transfer Learning

    Starting from a pretrained model instead of from zero.

    Video

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.