Gain fluency in both R and Python, for proficient use in later modules. Topics include random number generation, using vectors and matrices, working with APIs, and reading from/writing to different file formats.

The module also covers practices for ensuring code correctness, such as profiling, debugging and unit testing, and how to package code for distribution.

Gain familiarity with statistical and mathematical tools that will be used in later modules.

You’ll review the fundamentals of calculus, linear algebra, and probability theory, as well as other topics including matrix decomposition techniques, convergence of random variables, sample-based statistical inference, and numerical optimisation methods.

Produce convincing narrative summaries and informative visualisations for a variety of complex datasets.

You’ll learn how to evaluate the quality of a given dataset, diagnose and remedy missing and anomalous data, and consider the suitability of different exploratory analyses for various data types including spatial and temporal data.

Become familiar with data analysis and modelling, classification and resampling methods, and advanced topics like Random Forest and Support Vector Machines.

Gain the skills and knowledge to choose the appropriate supervised learning technique to effectively analyse and interpret data.

Build on your existing knowledge of ethics in data science and artificial intelligence and explore real-world issues.

Learn statistical concepts such as parameter estimation with large scale data and explore data sampling strategies in a Big Data world.

Design and develop data analysis procedures using Big Data technology (Hadoop and Spark), learn to utilise Big Data technology to perform a rigorous statistical analysis, and describe and apply mathematical techniques for fitting statistical models at scale and dealing with streaming data.

Select and explore an appropriate deep learning model architecture for a given supervised and unsupervised learning application.

You’ll be able to implement data and training pipelines for different types of neural networks, as well as implement appropriate evaluation measures and model selection strategies for supervised and unsupervised applications.

Assess the tools and techniques for solving unsupervised learning challenges, exploring topics including clustering, dimension reduction and density estimation.

Complete your studies examining the ethical implications of data science and artificial intelligence.

Learn the mathematics of techniques dealing with three unstructured data types: images, networks, and text.

Master deep learning and well-established statistical methods to tackle unstructured data and implement statistical and machine learning tasks.

Investigate key decision-making frameworks and develop expertise for taking machine learning beyond the prediction process to formal decision-making processes.