Computer Science

Data science has unlocked exciting possibilities for social scientists through its diverse toolkit, including big data analysis, visualisation, and machine learning models, enabling them to extract valuable insights from their data.  Yet, the success of a data-driven project hinges on data quality. This is where data engineering plays a pivotal role. Professionals must ensure that their acquired data is sufficient and accurate and must be adaptable to handle 'messy data' effectively. A substantial portion of time in data-driven projects (anecdotally 80%) is dedicated to cleaning and pre-processing data, with only 20% said to be devoted to building, evaluating, and deploying machine learning models. Despite the emergence of new AI technologies, which promise to automate many coding tasks, data manipulation is likely to remain an indispensable skill due to the inherent messiness of real-world data. By the end of this course, students will be proficient in producing a website to communicate your collected data and showcase your newly acquired data-wrangling abilities.

This introductory course provides a comprehensive introduction to digital research for students from a range of backgrounds. Through a variety of interactive sessions students develop an understanding of the key principles of Open Science and Scholarship, the importance of reproducibility and methods for managing research projects. The course serves as a platform for students to undertake digitally enabled research projects.

This course cover three important ideas in classical physics – Newton’s Laws of Motion, Newton’s Law of Gravitation and the Wave Equation. After considering analytical solutions to each, students look at computational solutions using the Python programming language (no background in coding is necessary) and touch on ideas such as dynamical systems and chaos. Students also look at solutions in different coordinate systems which give rise to familiar ideas such as Kepler’s laws of planetary motion and the inverse square law but from a first principles approach.

Much of modern machine learning rests upon a range of mathematical methods and many introductory machine learning courses seek to introduce algorithms before ensuring the link with these methods is made. This course offers students an introduction to traditional Machine Learning in a rigorous mathematical fashion. Assuming a familiarity with key results of linear algebra, differential calculus, probability and statistics, the course introduces the key areas of traditional machine learning and seeks to cover the key tools (and theorems) within these areas, and to illustrate these with practical exemplars. 

Are you looking to develop the skills to solve real-world challenges in finance, risk management, and insurance? These fields often deal with unpredictable phenomena—like investment decisions, insurance claim patterns, or pricing derivatives—which require robust stochastic models and advanced machine learning techniques. To tackle these challenges effectively, it’s essential to use robust statistical techniques and calibration methodologies to ensure models are reliable. This course equips students with the tools to apply modern statistical and machine learning methods to these complex problems. Students start by exploring Monte Carlo methods, simulating stochastic processes, and applying Generative Adversarial Networks (GANs) in risk management. They then connect Generalized Linear Models to deep neural networks, discovering their practical applications in the insurance industry. The course also addresses the challenges of calibrating models to ensure their accuracy and reliability. Combining rigorous theory with hands-on coding exercises in Python, students gain experience implementing real-world case studies while strengthening their core data science skills.

This course teaches students to define the phases of a typical compiler, including the front and back end. Students learn to identify tokens of a typical high level programming language define regular expressions for tokens and design implement a lexical analyzer using a typical scanner generator. The course explains the role of a parser in a compiler and relate the yield of a parse tree to a grammar derivation design and implement a parser using a typical parser generator, and how to apply an algorithm for a top down or a bottom up parser construction construct a parser for a small context free grammar. The course describes the role of a semantic analyzer and type checking create a syntax directed definition and an annotated parse tree describe the purpose of a syntax tree. The course focuses on the role of different types of runtime environments and memory organization for implementation of typical programming languages. The course describes the purpose of translating to intermediate code in the compilation process. Students design and implement an intermediate code generator based on given code patterns.