Proposed learning Outcomes

Distinguish between the concepts of “Artificial Intelligence”, “Machine Learning”, “Neural Networks”, “Deep Learning”
Distinguish between different types of learning (e.g. supervised, unsupervised, reinforcement) and recognise which applies to their own problem
Distinguish between linear and non-linear approaches and recognise which is best suited for application to their own problem

Describe what a feed-forward neural network (FFNN) is, along with its components (neurons, layers, weights, bias, activation functions, cost functions)
Explain how training of a FFNN works from a mathematical point of view (gradient descent, learning rate, backpropagation)
Execute with pen and paper a few steps of training of a very simple FFNN model
Tell the difference between a shallow and a deep network

Explain broadly how different NN architectures (feed-forward, convolutional, recurrent, autoencoders, etc) are wired and how they work
Apply the most appropriate architecture to a given problem/dataset
Implement different architectures in python with Keras and train them on given datasets
Analyze training curves and prediction outputs to evaluate if the training has been successful
Debug possible issues with the training and suggest changes to fix them

Explain the difference between training, validation and testing
Explain what overfitting is from a mathematical point of view, and what issues it causes
Apply the right tools to curb/fix overfitting issues
Identify what constitutes good practices of dataset design and how to avoid introducing information leakage or other biases when building your own datasets