Advanced Machine Learning

This is an advanced course on machine learning, focusing on recent advances in deep learning with neural networks, such as recurrent and Bayesian neural networks. The course will introduce the mathematical definitions of the relevant machine learning models and derive their associated optimization algorithms. Topics to be covered include Bayesian modelling and Gaussian processes, randomized methods, Bayesian neural networks, approximate inference, variational autoencoders, generative models, recurrent neural networks, backpropagation through time, long short-term memory, attention networks, memory networks, and neural Turing machines.