The course introduces students to deep learning and convolutional neural networks and presents an overview over systems for large-scale computing and big data.

The course mostly consists of asynchronous teaching material.

 -/-

-/-

100% Continuous Assessment

This will typically be made up of a project, assessed in terms of code and a report, (40%) and three homework exercises, including online quizzes (60%). Full details are provided in the programme handbook.

The aims of this course are:

■ to train students in the efficient implementation of computationally expensive data-analytic methods and/or data-analytic methods for big data;

■ to introduce students to deep learning and convolutional neural networks, both in terms of applications and implementation in frameworks such as Tensorflow or Keras; and 

■ to introduce students to enterprise-level technology relevant to big data analytics such as Spark, Hadoop or NoSQL databases.

By the end of this course students will be able to:

■ assess and compare the complexity of an algorithm and implementation both in terms of computational time and memory, as well as suggest strategies for reducing those;

■ distinguish between different types of deep and/or convolutional neural networks and choose an appropriate network for a given problem;

■ fit a neural network using specialised frameworks such as Tensorflow or Keras and assess the result;

■ discuss important methodological aspects underpinning deep learning; 

■ explain the differences between SQL and NoSQL databases and assess their suitability in different real-life settings; and

■ explain the basic concepts underpinning big data systems such as Spark or Hadoop and discuss their suitability and use in different scenarios.