📖Program Curriculum
Course modules
Compulsory modules
All the modules in the following list need to be taken as part of this course.
Statistical Learning Methods
Aim
This module aims to equip you with practical knowledge in statistics required for assessment and quantification of uncertainties in real life scenarios of data analysis. Module presents practically important algorithms of statistical learning for both prediction and decision making purposes and provides the opportunities for their experimental evaluation during the lab sessions. Tools for evaluation of learning algorithms’ performance are also considered and implemented to practical examples.
Syllabus
• Introduction to statistical learning
• Statistics fundamentals: probability, random variables, description statistics and stochastic processes
• Statistical inference: estimation and testing, evaluation metrics
• Bayesian methods: Naive Bayes and Bayesian Networks
• Markov processes and chains, Kalman estimators
• Statistical modelling and decision making: regression, mixture models and classification approaches
• Case study: application of statistical learning for aerospace sector problem.
Intended learning outcomes On successful completion of this module you should be able to:
1. Relate statistical techniques for uncertainty quantification to real life problems.
2. Differentiate experimental data according to the underlying models of stochastic processes.
3. Propose statistical learning methods suitable for particular problem.
4. Assess the outcomes of the statistical learning.
Systems Engineering
Aim
This module aims to enable you to apply the principles of Systems Engineering to system problems.
Syllabus
Topics covered by the course include:
Systems challenges
The systems process
Understanding systems
Capability need and requirements
System design and architecture
System evaluation, verification and validation
The impact of organisation on Systems Engineering
People, skills and competencies in Systems Engineering.
Intended learning outcomes On successful completion of this module you should be able to:
1. Illustrate common deficiencies in system design using case studies.
2. Formulate approaches to system design based upon capability, behavioural principles and architectural considerations.
3. Collect comprehensive system requirements from stakeholders formulate their flow-down into the systems design
4. Design verification strategies for proving the systems design
5. Organise projects to achieve a successful systems design.
Intelligent Cyber Physical Systems
Aim
The aim of this module is to enable you to think critically about technology, solutions, and gain best practices of intelligent systems issues relating to the cyber-physical systems.
Syllabus
Cyber-physical systems: Control, sensor and actuators
Intelligent agent and multi-agent
Intelligent robotics
Embedded systems
Connected system
Countermeasures.
Intended learning outcomes
On successful completion of this module you should be able to:
Appraise the theoretical and practical aspects for intelligent system in cyber-physical systems approach.
Distinguish the fundamental aspect of intelligent agent, robotics, multi agent systems.
Create working knowledge in dependable control, and embedded systems.
Assess key issues of connected system within the physical world.
Analyse different approaches of cyber-physical system with consideration of countermeasures.
Search and Optimisation
Aim
The module aims at giving you a solid background introduction to optimization and decision theory. The use of modern optimisation methods, especially for applications in artificial intelligence. More than the traditional linear techniques, non-linear techniques will also be addressed, including multi-criteria methods.
Syllabus
Introduction to Optimisation and Decision Theory
Optimisation models and methods
Integer and Mixed-integer programming
Linear and non-linear programming (including intro to Meta-heuristics)
Decision analysis
Multiple-criteria decision analysis.
Intended learning outcomes
On successful completion of this module you should be able to:
Formulate decision problems based on optimisation scenarios, identifying the different variables.
Differentiate and apply different optimisation models and methods.
Evaluate optimisation and decision problem criteria.
Design decision analysis problems and apply/implement different algorithms and solutions.
Examine and debate the application of structured approaches to support decision in context of multiple conflicting objectives.
Logic and Automated Reasoning
Aim
This module aims at providing the foundations of logic and reasoning modelling to understand how reasoning can be automated. Moreover it introduces the fundamental techniques and formal language to design automated reasoners.
Syllabus
Introduction to logical representation and reasoning
Logical Agents
Propositional Logic
First-order Logic
Inference Algorithms
Engineering domain knowledge representation
Exercises and case studies
Intended learning outcomes
On successful completion of this module a student should be able to:
1. Analyse syntax and semantics of different problem instances using the appropriate formal language to identify relevant knowledge
2. Building essential but complete Knowledge Bases representing a given knowledge, using Propositional and First Order Logics as representation languages.
3. Design strategies to enable automated solving of assigned reasoning problems, detailing the execution steps to perform the given tasks.
Data Analytics and Visualisation
Aim
This module will introduce you to data analytics, overview challenges and solutions in this area, present approaches to predictive and descriptive data mining and explain unsupervised learning techniques suitable for new information discovery. Visualisation tools and performance metrics are also considered within the module. You may benefit from knowledge of basic concepts of statistics for performance assessment and evaluation.
Syllabus
Introduction to Data Analytics
Data exploration and pre-processing
Predictive analytics: regression and classification methods
Clustering and dimensionality reduction
Graph analysis and visualisation
Software and tools for data analytics
Case study: application of data analytics techniques and visualisation tools for knowledge discovery problem.
Intended learning outcomes
On successful completion of this module you should be able to:
1. Distinguish stages of the data analytics workflow
2. Categorize data analysis and visualisation techniques with respect to data analytics stages
3. Plan data analytics workflow based on the available data and formulated requirements
4. Set up algorithms for discovery of new information from the large data sets
5. Evaluate performance of the algorithms and quality of the data analysis outcomes.
Deep Learning
Aim
The aim of this module is to introduce you to machine learning algorithms, with particular emphasis on supervised learning and deep learning, suitable for real life problems concerning relevant industrial applications from aerospace, manufacturing or transports.
Syllabus
Artificial Neural Networks (Shallow models)
Backpropagation and Training
Deep learning architectures
Convolutional Neural Networks
Recurrent neural networks
Deep learning applications: object detection, identification, classification, tracking, prediction
Introduction to Reinforcement learning
Tensorflow practical sessions on Artificial, Convolutional and Recurrent Neural Networks.
Intended learning outcomes
On successful completion of this module you should be able to:
1. Explain fundamental meaning and discuss applicability of machine learning algorithms for industrial applications.
2. Test the commonly used AI algorithms and describe their applications.
3. Implement AI algorithms, estimate their performance in a simulation environment and assess their performance for a realistic case study.
4. Judge AI implementation platforms and create deep learning applications for specific problems.
Ethical, Regulatory and Social Aspects of AI
Show less
