This module covers the statistics and probability required for a Masters in Engineering. The learner will gain the expertise to interpret the probabilistic models used in the engineering literature. It will cover statistical methods to analyse and quantify processes. It will enable learners to model problems using probabilistic and statistical mathematical methods.

1. Apply probability theory to analsye the centrality,dispersion and relationships withinand between datasets and distributions.

2. Apply experimental design and statistical inference to make inferences from data.

3. Analyse the bias and variance of maximum likelihood and Bayesian estimators.

4. Analyse stochastic processes (including Markovprocesses).

5. Evaluate, select and apply appropriate statistical techniques to problems in the application field of study.

6. Interpret the probability and statistics used in state of the art research publications and reproduce findings.

7. Model an application specific problem with statisticsand probability techniques.

Programming for Data Science will introduce the learner to the core concepts of data science programming. The student will be introduced to the Python programming language (specifically SciPy) generally, and will employ functions to manipulate lists, before implementing multi-dimensional arrays using Numpy or similar in order to perform statistical operations and linear equations. The student will then manipulate data frames and time-series data using pandas or similar. The student will learn techniques for reading in data from multiple sources, scraping data from APIs and unstructured websites. Databases will be introduced with SQL programming. Creating, modifying and querying the database through Python and preparing the database results within the SciPy structures for future data analysis. The module will assume the student will have some experience with at least one programming language.

1. Create and manipulate vectors, matrices and n-dimensional tensors using a data science programming language 

2. Employ appropriate functions to implement linear algebra and statistical procedures 

3. Employ appropriate packages to create, read and manipulate tabular and time-series data 

4. Evaluate and implement techniques to gather and store information from various unstructured data sources 

5. Design and deploy database systems ensuring durability, high availability and high performance

6. Interrogate database systems using an appropriate querying language 

7. Describe techniques to analyse the efficiency of algorithms and to compare the effectiveness of different algorithms 

The subject covers the linear algebra required for post-graduate engineering courses. The learner will gain the expertise to interpret the linear algebra models used in the engineering literature. It will also enable learners to model problems using linear algebra methods.

1. Solve systems of linear equations and analyse the solutions.

2. Analyse affine transformations in three dimensions.

3. Interpret the linear algebra in state of the art research publications andreproduce findings.

4. Explain the use of vector spaces in analysing solutions to systems of equations.

5. Use projections to find the least squares solution of overdetermined systems.

6. Decompose matrices into their singular value decompositions and interpret.

7. Apply matrices to the Fourier transform, graphs and networks.

This module covers the data analysis and visualisation skills required for a Masters in Data Science. This topic will introduce the learner to the SOTA data analysis tools and techniques, which help to interpret and extract meaningful information from data (using public datasets). The learner will gain expertise in data preprocessing, exploratory data analysis and visualisation, pattern recognition and discriminative classification. The learner will work on designing and creating interactive dashboards for data visualisation and also on solving real-world data analysis and classification problems.

1. Apply techniques such as feature scaling, standardisation, missing data handling and encoding to preprocess and cleandata.

2. Visualise the processed data graphically, identify the correlation between the features, interpret the linear/non-linear relationships in the data.

3. Make meaningful inferences from the data, remove/retain features based on variable importance.

4. Create interactive dashboard for data visualisation.

5. Identify patterns in the data using exploratory data analysis and clustering techniques.

6. Discriminate patterns in new data using trained discriminative classificationmodels.

7. Summarise, analyse, and relate research in the area of exploratory data analysis and pattern recognition in writing. Appreciate the data ethics and constraints that apply to the use of data in real-world scenarios.

8. Design, implement and test a real world problem using the above learned techniques.

This module introduces the topic of machine learning algorithms (algorithms that learn from data), with the first part of the module dedicated to the standard shallow forms of machine learning before moving on to Deep Learning and Convolutional Neural Networks for use in computer vision tasks, particularly recognition, classification and localisation. The emerging topic of Deep Reinforcement Learning will be briefly introduced. The module will look at training strategies and frameworks for Deep Learning. As well as the technical/scientific elements, students will reflect on the ethical implications of machine learning.

1. Compare state of the hand engineered detectors with machine learning techniques in terms of performance on appropriate metrics and data sets and determine the appropriateness of each for safety critical applications.
2. Apply transfer learning to adapt a pre-trained network to a new classification problem.
3. Assess the validity of various cost functions to specific machine learning problems.
4. Effectively collaborate and communicate with others in the timely development of solutions to machine learning problems, including reports and software.
5. Design, test and evaluate deep network architectures.
6. Appreciate the data rights of citizens and the constraints these apply to the use of pattern detection in real world scenarios.

Data science involves exploring problems in particular knowledge domains, identifying how data can be analysed to help solve these problems and building and evaluating appropriate models to achieve insights. To ensure the integrity and accuracy of data science research, it is essential that the student develops a deeper understanding of the fundamentals of research methods and ethics. This module introduces skills needed to develop meaningful research questions within particular problem domains, and to design appropriate research strategies and designs to address these. A critical approach that considers and deals with issues such as methodology suitability, data quality, data validity, data ethics (e.g. data bias, algorithmic bias, privacy) and potential unintended consequences is emphasised. An understanding of both qualitative and quantitative research methods and how these can be applied in a data science context will be developed through examining how data can be gathered and critically analysed, and how the validity of conclusions drawn using particular models can be assessed. Mechanisms for dissemination and communication of research outcomes will also be covered.

1. Undertake a literature search and generate a literature review on a research topic.

2. Formulate an appropriate research question or hypothesis.

3. Designand critically apply an appropriate research strategy.

4. Identify any ethical issues that need to beaddressed, andensure these are integrated into research plans/activities.

5. Devise and/orutilisemethods for data collection and analysis incorporating qualitative and quantitative approaches.

6. Devise a strategy for evaluation and critical appraisal of research outcomes.

This module introduces students to the architectures and tools underpinning the management and processing of large scale datasets, which are too big for conventional approaches. Students will understand these architectures and tools and be able to use them to code solutions, query data from structured, unstructured, and streamed sources, and analyse that data using appropriate algorithms.

Students will also be able to evaluate a variety of Big Data Cloud platform providers e.g. Amazon AWS, Microsoft Azure, in order to deploy and host data solutions.

1. Discuss the problem of managing data at scale and why traditional data management systems are insufficient

2. Evaluate state of the art architectures, tools & frameworks for working with Big Data

3. Implement Big Data solutions using a synthesis of different data paradigms e.g. distributed data and streaming data, structured and unstructured data

4. Compare a variety of Big Data query languages and identify optimum query approaches for a variety of scenarios

5. Outline some well-known Big Data problem scenariosfrom a variety of domains, and from student’s own experience,and evaluate some standard, state-of-the-art approaches to solving them with appropriate architectures, tools, & frameworks

6. Evaluate some of the human and organisational issues involved in integrating Big Data solutions across the enterprise, and in current research questionsfrom the domain e.g. ethics, privacy, bias, and cybersecurity