Data Science - BSc (Hons)

with a Foundation Year

This module equips students with an understanding of how modern cloud-based applications work. Topics covered may include:

A high-level view of cloud computing: the economies of scale, security issues, ethical concerns, the typical high-level architecture of a cloud-based application, types of available services (e.g., parallelization, data storage).

Cloud infrastructure: command line interface; containers and virtual machines; parallelization (e.g., MapReduce, distributed graph processing); data storage (e.g., distributed file systems, distributed databases, distributed shared in-memory data structures).

Cloud concepts: high-level races, transactions and sequential equivalence; classical distributed algorithms (e.g., election, global snapshot, consensus, distributed mutual exclusion); scheduling, fault-tolerance and reliability in the context of a particular parallelization technology (e.g., MapReduce).

Operating system support: network services (e.g., TCP/IP, routing, reliable communication), virtualization services (e.g., virtual memory, containers).

This module introduces widely-used mathematical methods for functions of a single variable. The emphasis is on the practical use of these methods; key theorems are stated but not proved at this stage. Tutorials and Maple worksheets will be used to support taught material.

Complex numbers: Complex arithmetic, the complex conjugate, the Argand diagram, de Moivre's Theorem, modulus-argument form; elementary functions

Polynomials: Fundamental Theorem of Algebra (statement only), roots, factorization, rational functions, partial fractions

Single variable calculus: Differentiation, including product and chain rules; Fundamental Theorem of Calculus (statement only), elementary integrals, change of variables, integration by parts, differentiation of integrals with variable limits

Scalar ordinary differential equations (ODEs): definition; methods for first-order ODEs; principle of superposition for linear ODEs; particular integrals; second-order linear ODEs with constant coefficients; initial-value problems

Curve sketching: graphs of elementary functions, maxima, minima and points of inflection, asymptotes.

This module provides an introduction to object-oriented software development. Software pervades many aspects of most professional fields and sciences, and an understanding of the development of software applications is useful as a basis for many disciplines. This module covers the development of simple software systems.

Students will gain an understanding of the software development process, and learn to design and implement applications in a popular object-oriented programming language. Fundamentals of classes and objects are introduced and key features of class descriptions: constructors, methods and fields. Method implementation through assignment, selection control structures, iterative control structures and other statements is introduced. Collection objects are also covered and the availability of library classes as building blocks. Throughout the course, the quality of class design and the need for a professional approach to software development is emphasised and forms part of the assessment criteria.

Introduction to Probability. Concepts of events and sample space. Set theoretic description of probability, axioms of probability, interpretations of probability (objective and subjective probability).

Theory for unstructured sample spaces. Addition law for mutually exclusive events. Conditional probability. Independence. Law of total probability. Bayes' theorem. Permutations and combinations. Inclusion-Exclusion formula.

Discrete random variables. Concept of random variable (r.v.) and their distribution. Discrete r.v.: Probability function (p.f.). (Cumulative) distribution function (c.d.f.). Mean and variance of a discrete r.v. Examples: Binomial, Poisson, Geometric.

Continuous random variables. Probability density function; mean and variance; exponential, uniform and normal distributions; normal approximations: standardisation of the normal and use of tables. Transformation of a single r.v.

Joint distributions. Discrete r.v.'s; independent random variables; expectation and its application.

Generating functions. Idea of generating functions. Probability generating functions (pgfs) and moment generating functions (mgfs). Finding moments from pgfs and mgfs. Sums of independent random variables.

Laws of Large Numbers. Weak law of large numbers. Central Limit Theorem.

An introduction to databases and SQL, focussing on their use as a source for content for websites. Creating static content for websites using HTML(5) and controlling their appearance using CSS. Using PHP to integrate static and dynamic content for web sites. Securing dynamic websites. Using Javascript to improve interactivity and maintainability in web content.

Introduction to R and investigating data sets. Basic use of R (Input and manipulation of data). Graphical representations of data. Numerical summaries of data.

Sampling and sampling distributions. ?² distribution. t-distribution. F-distribution. Definition of sampling distribution. Standard error. Sampling distribution of sample mean (for arbitrary distributions) and sample variance (for normal distribution) .

Point estimation. Principles. Unbiased estimators. Bias, Likelihood estimation for samples of discrete r.v.s

Interval estimation. Concept. One-sided/two-sided confidence intervals. Examples for population mean, population variance (with normal data) and proportion.

Hypothesis testing. Concept. Type I and II errors, size, p-values and power function. One-sample test, two sample test and paired sample test. Examples for population mean and population variance for normal data. Testing hypotheses for a proportion with large n. Link between hypothesis test and confidence interval. Goodness-of-fit testing.

Association between variables. Product moment and rank correlation coefficients. Two-way contingency tables. ?² test of independence.

To be confirmed.

Built on the foundation of object-oriented software development, this module provides an introduction software development for Artificial Intelligence (AI). In this module, students will gain an understanding of data analysis and statistics techniques, including summarising data, using measures of central tendency and dispersion, and effective graphical representations. Various probability models, including normal and binomial distributions, sampling and inference and predictive techniques are introduced.

Throughout the module, students will learn to embed data analysis and statistics concepts into a programming language which offers good support for AI (e.g., Python). Students will learn to use important AI-purposed libraries and tools, and apply these techniques to data loading, processing, manipulation and visualisation.

Building scaleable web sites using client-side and and server-side frameworks (e.g. JQuery, CodeIgniter). Data transfer technologies, e.g. XML and JSON. Building highly interactive web sites using e.g. AJAX. Web services. Deploying applications and services to the web: servers, infrastructure services, and traffic and performance analysis. Web and application development for mobile devices.

This module aims to strengthen the foundational programming-in-the-small abilities of students via a strong, practical, problem solving focus. Specific topics will include introductory algorithms, algorithm correctness, algorithm runtime, as well as big-O notation. Essential data structures and algorithmic programming skills will be covered, such as arrays, lists and trees, searching and sorting, recursion, and divide and conquer.

.

.

This module covers the basic principles of machine learning and the kinds of problems that can be solved by such techniques. You learn about the philosophy of AI, how knowledge is represented and algorithms to search state spaces. The module also provides an introduction to both machine learning and biologically inspired computation.

This module provides an introduction to the theory and practice of database systems. It extends the study of information systems in Stage 1 by focusing on the design, implementation and use of database systems. Topics include database management systems architecture, data modelling and database design, query languages, recent developments and future prospects.

This module is designed to provide students with an introduction to the use of data analytics tools on large data sets including the analysis of text data. The module will begin by discussing the principles of text-mining and big data. The module will then discuss the techniques that can be used to explore large data sets (including pre-processing and cleaning) and the use of multivariate statistical techniques for supervised and unsupervised learning. The module will conclude by considering several data mining techniques.

Constructing suitable models for data is a key part of statistics. For example, we might want to model the yield of a chemical process in terms of the temperature and pressure of the process. Even if the temperature and pressure are fixed, there will be variation in the yield which motivates the use of a statistical model which includes a random component. In this module, students study linear regression models (including estimation from data and drawing of conclusions), the use of likelihood to estimate models and its application in simple stochastic models. Both theoretical and practical aspects are covered, including the use of R.