Handbook

ZEIT4154 (Deep Learning) is a 6 Units of Credit (UoC) course. Deep learning is an area of artificial intelligence that focuses on a particular family of machine learning models that are able to learn to perform complex tasks from many application areas including computer vision, natural language, genomic modelling, financial modelling and many more. In the past decade deep learning models have improved on state-of-the-art results in many complex tasks in these areas.  

This course introduces the students to various aspects of neural networks and deep learning, including optimisation and algorithms for training and regularisation, deep feedforward neural networks, convolution neural networks, recurrent neural networks, deep reinforcement learning, autoencoders and deep generative models. 

Students will learn to apply these techniques to a wide variety of real-world applications.  

Note that some relevant machine learning knowledge is reviewed only briefly in class. Students who have no knowledge of machine learning and are not taking ZEIT4151 may find that doing 2-3 hours of reading on the topic at the start of the semester is useful to supplement their understanding. If you would like the recommended reading ahead of time please reach out to the course coordinator.