Artificial neural networks#
In this session we learn about artificial neural networks.
Learning goals for this session#
Become familiar with ANNs:
mathematical notation in matrix-vector form
weights & biases (slopes & intercepts), score, activation function, hidden layers, prediction
Be able to use PyTorch to implement a feed-forward ANN:
building the model by hand
using built-in helper functions (nn.Module, DataLoader …)
This unit requires basic familiarity with concepts and notation from linear algebra. To recap, there is a short section on algebra recap with a handout and some further references.
Slides#
Here are the slides for this session.
Practical exercises#
There are two notebooks for exercises. First, we will implement a multi-layer feed-forward network “by hand”. Then, we will implement the same model (for the same training data) by using PyTorch’s helper functions.