Glossary of Terms

Credits

You must earn a defined number of credits (aka ECTS) to complete each year of your course. You do this by taking all of its required modules as well as the correct number of optional modules to obtain that year's total number of credits.

Module

An examinable portion of a subject or course, for which you attend lectures and/or tutorials and carry out assignments. E.g. Algebra and Calculus could be modules within the subject Mathematics. Each module has a unique module code eg. MA140.

Optional

A module you may choose to study.

Required

A module that you must study if you choose this course (or subject).

Semester

Most courses have 2 semesters (aka terms) per year.

Year 1 (90 Credits)

RequiredCT5142: Artificial Intelligence and Ethics

CT5142: Artificial Intelligence and Ethics

Semester 1 | Credits: 5

Artifical intelligence technologies have evolved dramatically in recent years, impacting on many areas of human life. Societal responses to these developments have ranged from enthusiastic optimism to deep suspicion. The module will explore prominent ethical issues arising in relation to the design, use and societal impact of Artificial Intelligence. Topics addressed in the module include Embedded values, ethics by design and trustworthiness of AI; Privacy, consent, dark patterns and contextual integrity; Algorithmic fairness, bias and algorithmic governance; Assistance and surveillance; Datafication, surveillance capitalism and monopoly; AI and the workplace; generative AI; autonomous artificial agents and responsibility; AI and the environment; AI risk and safety.
(Language of instruction: English)

Learning Outcomes

1. Demonstrate competence in using specialist ethical concepts
2. Identify and summarise important ethical concerns related to the design, use and societal impact of Artificial Intelligence.
3. Apply relevant theoretical models from the ethical, legal and social science literature to identified ethical concerns regarding AI.
4. Critically analyse strengths and weaknesses of different positions from the ethical, legal and social science literature on ethical concerns related to the design, use and societal impact of Artifical Intelligence.
5. Demonstrate the ability to communicate ethical concerns coherently and concisely for professional and lay audiences.

Assessments

• Continuous Assessment (100%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  HEIKE SCHMIDT-FELZMANN 🖂
  
•  DEIRDRE KING 🖂
  
•  GERALDINE HEALY 🖂
  

Reading List

1. "The Oxford Handbook of Ethics of AI" by Markus Dubber, Frank Pasquale, Sunit Das (eds)
   Publisher: OUP
2. "Automating Inequality: How High-Tech Tools Profile, Police, and Punish the Poor" by Virginia Eubanks
   Publisher: St Martin's Press
3. "Ethics of Artificial Intelligence" by Matthew Liao (ed.)
   Publisher: OUP
4. "Robot Ethics 2.0: From Autonomous Cars to Artificial Intelligence" by Patrick Lin, Keith Abney, Ryan Jenkins (Editors)
   Publisher: Oxford University Press
5. "Privacy in Context: Technology, Policy, and the Integrity of Social Life" by Helen Nissenbaum
   Publisher: Stanford University Press
6. "The Oxford Handbook of Digital Ethics" by Carissa Veliz (ed.)
   Publisher: OUP
7. "Privacy as Trust: Information Privacy for an Information Age" by Ari Waldman
   Publisher: Cambridge University Press
8. "The Age of Surveillance Capitalism" by Shoshanna Zuboff
   Publisher: Profile Books

The above information outlines module CT5142: "Artificial Intelligence and Ethics" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

RequiredCT5132: Programming and Tools for AI

CT5132: Programming and Tools for AI

Semester 1 | Credits: 5

This module is about programming and computational tools required for artificial intelligence. It uses the Python language as the main vehicle, but focusses on conceptual material rather than just the language itself. It moves fast through introductory Python workings. It covers several important Python libraries in detail, especially for numerical computing, machine learning, plotting, graphs. It discusses approaches to building re-usable, high quality code but not software engineering per se. It also visits some extra topics such as version control and introduction to the R language for statistics. The module is core for the University of Galway MSc in Artificial Intelligence (MScAI) Part-time (online) and Full-time (classroom). The syllabus and assessment will be the same for both.
(Language of instruction: English)

Learning Outcomes

1. Read and write simple Python programs, e.g. for data munging, with a high degree of comfort.
2. Use R for simple statistics and data exploration.
3. Use numerical Python libraries for manipulation, input/output, visualisation of numerical data using Numpy array types.
4. Use essential tools for AI, including libraries for data gathering, numerical computing, machine learning, combinatorial programming, and modelling networks.
5. Plan/design a program using any of the above facilities; test it; document it; execute it locally or in the cloud as appropriate.

Assessments

• Written Assessment (50%)
• Continuous Assessment (50%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  MICHAEL MADDEN 🖂
  
•  MICHAEL SCHUKAT 🖂
  
•  JAMES MCDERMOTT 🖂
  

Reading List

1. "Think Python" by Allen Downey
2. "A Whirlwind Tour of Python" by Jake Vanderplas

The above information outlines module CT5132: "Programming and Tools for AI" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

RequiredCT5120: Introduction to Natural Language Processing

CT5120: Introduction to Natural Language Processing

Semester 1 | Credits: 5

Natural Language Processing (NLP) is concerned with the automatic analysis, interpretation and annotation of textual data. Applications of NLP are in the extraction of information from text, linking text to databases or other structured knowledge, classification, summarization, translation and generation of text, etc. This module introduces students to the field of NLP, including linguistic, statistical and machine learning foundations, primary challenges and approaches to the syntactic and semantic analysis of textual data, and applications in summarization, chatbot development, knowledge extraction and opinion mining. The course ends with a discussion of ethical aspects in NLP.
(Language of instruction: English)

Learning Outcomes

1. Ability to explain the various levels of linguistic structure relevant to NLP.
2. Ability to use standard algorithms for basic NLP analysis
3. Gain practical knowledge of and experience in the use of NLP toolkits
4. Ability to explain a selection of theoretical principles behind core NLP applications.
5. Ability to apply NLP algorithms, toolkits and applications to tasks in AI, Data Analytics and other related application areas.

Assessments

• Written Assessment (50%)
• Continuous Assessment (50%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  DEIRDRE KING 🖂
  
•  PETER PAUL BUITELAAR 🖂
  
•  GERALDINE HEALY 🖂
  
•  John McCrae 🖂
  

The above information outlines module CT5120: "Introduction to Natural Language Processing" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

RequiredCT5129: Artificial Intelligence Project

CT5129: Artificial Intelligence Project

15 months long | Credits: 30

This capstone research project tests the students ability to carry out in depth analysis, problem-solving and reporting of an AI problem.
(Language of instruction: English)

Learning Outcomes

1. Identify and research an Artificial Intelligence (AI) problem
2. Identify, describe, and synthesize the state-of-the-art approaches to the problem
3. Devise and implement a solution to the problem which has novelty
4. Carry out an appropriate (e.g., experimental) evaluation on the solution
5. Write up the problem, state-of-the-art, methodology and implementation, (experimental) evaluation, results and their discussion, and conclusion as a thesis.

Assessments

• Research (100%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  MATTHIAS NICKLES 🖂
  
•  DEIRDRE KING 🖂
  
•  GERALDINE HEALY 🖂
  

The above information outlines module CT5129: "Artificial Intelligence Project" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

RequiredCT4100: Information Retrieval

CT4100: Information Retrieval

Semester 1 | Credits: 5

The course introduces some of the main theories and techniques in the domain of information retrieval.
(Language of instruction: English)

Learning Outcomes

1. Explain the main models used in information retrieval.
2. Explain the factors involved in designing and analysing weighting schemes
3. Be able to choose suitable data structures and algorithms for building IR systems
4. Explain the main ideas and approaches used in web search
5. Explain the main ideas and approaches used in recommender systems
6. Explain the concepts in applying learning mechanisms in information retrieval

Assessments

• Written Assessment (70%)
• Continuous Assessment (30%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  COLM O'RIORDAN 🖂
  
•  DEIRDRE KING 🖂
  
•  GERALDINE HEALY 🖂
  

The above information outlines module CT4100: "Information Retrieval " and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

RequiredCT5165: Principles of Machine Learning

CT5165: Principles of Machine Learning

Semester 1 | Credits: 5

Machine Learning is concerned with algorithms that improve their performance over time, as they are exposed to new data. This module introduces learners to the different categories of machine learning tasks and provides in-depth coverage of important algorithms for tackling them. Its focus is on the theory underlying ML algorithms. In addition, the learners gain experience of implementing algorithms from scratch, as well as using ML software tools to select and apply these algorithms in applications, and they evaluate and interpret the results. Topics include: 1. Overview of Machine Learning & Major Categories of Task 2. Supervised Learning Principles and Information-Based Learning 3. Similarity-Based Learning 4. Evaluating Classifier Performance, Practical Advice, and Some Machine Learning Tools 5. Linear Regression in One and Multiple Variables 6. Linear Classifiers with Hard and Soft Thresholds 7. Probabilistic Machine Learning
(Language of instruction: English)

Learning Outcomes

1. Define Machine Learning and explain what major categories of learning tasks entail
2. Demonstrate how to apply the machine learning and data mining process to practical problems
3. Explain and apply algorithms including decision tree learning, instance-based learning, probabilistic learning, linear regression, logistic regression, and others
4. Given a dataset and task to be addressed, select, apply and evaluate appropriate algorithms, and interpret the results
5. Discuss ethical issues and emerging trends in machine learning.

Assessments

• Written Assessment (70%)
• Continuous Assessment (30%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  DEIRDRE KING 🖂
  
•  GERALDINE HEALY 🖂
  
•  Ihsan Ullah 🖂
  

The above information outlines module CT5165: "Principles of Machine Learning" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

RequiredCT5135: Research Topics in AI

CT5135: Research Topics in AI

Semester 2 | Credits: 5

Research Topics in AI will provide an in-depth coverage of two or three active research areas in the field of AI. For each topic the module provides an overview of research in the area and the implications from real-world implementations.
(Language of instruction: English)

Learning Outcomes

1. Gain both a wide and a deep knowledge of the topic(s) in the current offering of the module.
2. Improve their skills at navigating through, and critically examining, the scientific literature on the selected topic(s).
3. Demonstrate the use of techniques from the selected topic(s) using real-world datasets and tools.
4. Gain practical knowledge from invited speakers from academia and industry regarding state of the art tools and applications.
5. Familiarise to challenges in relation to Smart Energy and Grids, and be able to demonstrate some applications in this area using appropriate codebase or datasets.
6. Outline challenges relating to business and big data, with attention to issues such as fraud detection etc.
7. Learn challenges relating to Smart Cities, and demonstrate the use of Machine Learning through the use of Intelligent Transportation Networks.
8. Experience challenges related to business and big data, with attention to issues such as health care, fraud detection, autonomous vehicles, etc.

Assessments

• Continuous Assessment (100%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  DEIRDRE KING 🖂
  
•  GERALDINE HEALY 🖂
  
•  Ihsan Ullah 🖂
  

The above information outlines module CT5135: "Research Topics in AI" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

RequiredCT5100: Data Visualisation

CT5100: Data Visualisation

Semester 2 | Credits: 5

Visualisation is a fundamental technique in presenting the properties of data and the results and evaluation of data analytical processes. For a data visualisation to be successful the analyst needs to have considered the properties of the data, the information to be communicated, the mode of visualisation delivery and the expectations of the audience. This module takes a practical approach to introducing learners to the strengths and weaknesses of human perception, and the use of best practices to represent complex and large data stories using visual primitives. The module demonstrates the role of visualisation in exploratory data analysis and its fundamental role in explaining data analytical outcomes. The module emphasises the need to communicate clearly, while adhering to the ethical requirement to present data-derived information truthfully and without bias. The examples covered during the module have been generated using the R language. However, students can use other languages and visualisation applications in their assignment work.
(Language of instruction: English)

Learning Outcomes

1. Describe the basic design principles underlying human perception, color theory and narrative
2. Analyse the effectiveness of different visual elements in communicating analytical information
3. Select the best visualisation strategy to use for different exploratory and explanatory scenarios
4. Execute different types of data visualisations for use in various exploratory and explanatory scenarios
5. Carry out basic data preprocessing and wrangling necessary to produce effective visualisations
6. Discuss the ethical issues of representing data and information truthfully when creating a visualisation
7. Critically evaluate data visualisations produced by other people

Assessments

• Written Assessment (65%)
• Continuous Assessment (35%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  DEIRDRE KING 🖂
  
•  CONOR HAYES 🖂
  
•  GERALDINE HEALY 🖂
  

Reading List

1. "R Graphics Cookbook" by Winston Chang
   Publisher: O'Reilly
2. "ggplot2" by Hadley Wickham
   ISBN: 9783319242750.
   Publisher: Springer
3. "Information Visualization" by Colin Ware
   ISBN: 9780123814647.
   Publisher: Elsevier
4. "Now You See it" by Stephen Few
   ISBN: 9780970601988.
   Publisher: Analytical Press
5. "The Visual Display of Quantitative Information" by Edward R. Tufte
   ISBN: 9781930824133.
   Publisher: Graphics Press

The above information outlines module CT5100: "Data Visualisation" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

RequiredCT5134: Agents, Multi-Agent Systems and Reinforcement Learning

CT5134: Agents, Multi-Agent Systems and Reinforcement Learning

Semester 2 | Credits: 5

The topic of Agents and Multi-Agent Systems, examines environments that involve autonomous decision making software actors to interact with their surroundings with the aim of achieving some individual or overall goal. A typical agent environment could be a trading environment where an agent attempts to optimise energy usage, or the profitability of a transaction. More recently, significant global attention has focused on the vision of autonomous vehicles, which also follows the core principle of an agent attempting to achieve a set of defined goals. This module begins by examining the underpinnings of what is an Agent, and how we can better understand the principles of an agent and its autonomy. Multi-Agent Systems are then explored, as a means of understanding how many agents can interact with each other in a complex environment. Agents are commonly modelled using Game Theory, and in this module a range of Game Theoretic Models will be studied. The module will also examine Adaptive Learning Agents through the use of Reinforcement Learning, which focuses on training learners to choose actions which yield the maximum reward in the absence of prior knowledge. The module takes a hands-on, practical approach to reinforcement learning theory, beginning with Markov Decision Processes, detailing practical learning examples and how to formulate a reinforcement learning task.
(Language of instruction: English)

Learning Outcomes

1. Explain and discuss the principles underlying Agents.
2. Explain the role of game theory and games in agent design.
3. Apply the principle of agents to a range of simulation problems.
4. Formulate a decision making problem as a Markov decision process (MDP)
5. Apply reinforcement learning algorithms to learn policies for MDPs
6. Conduct experiments to determine appropriate hyperparameters for a reinforcement learning algorithm

Assessments

• Written Assessment (70%)
• Continuous Assessment (30%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  DEIRDRE KING 🖂
  
•  ENDA HOWLEY 🖂
  
•  GERALDINE HEALY 🖂
  
•  PATRICK MANNION 🖂
  

The above information outlines module CT5134: "Agents, Multi-Agent Systems and Reinforcement Learning " and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

RequiredCT5133: Deep Learning

CT5133: Deep Learning

Semester 2 | Credits: 5

This is an advanced module in machine learning, focusing on neural networks (NNs), deep NNs, and connectionist computing. Students learn about the basic principles and building blocks of deep learning, and how to implement a deep neural network ‘from scratch’. They also learn about software libraries and tools, and gain experience of applying deep learning in a range of practical applications. The module includes substantial practical programming assignments. This module is intended for students who have completed a first course in machine learning, and already have a good grounding in supervised learning topics including: classification and regression; evaluation of classifiers; overfitting and underfitting; basic algorithms such as k-nearest neighbours, decision tree learning, logistic regression, and gradient descent.
(Language of instruction: English)

Learning Outcomes

1. Explain key Machine Learning concepts that relate to Deep Learning
2. Explain the operation of feed-forward neural networks and the back-propagation algorithm
3. Describe, implement and apply key features of deep neural networks
4. Implement NNs for supervised machine learning tasks, from first principles and (separately) using modern libraries and frameworks
5. Choose, explain and implement: (a) recurrent and other NN architectures for sequential data; (b) self-supervised NN architectures for unlabelled data; (c) supervised NN architectures for representation learning
6. Discuss ethical issues, limitations, and emerging trends in deep learning.

Assessments

• Written Assessment (60%)
• Continuous Assessment (40%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  MICHAEL MADDEN 🖂
  
•  DEIRDRE KING 🖂
  
•  GERALDINE HEALY 🖂
  
•  JAMES MCDERMOTT 🖂
  
•  Bharathi Raja Asoka Chakravarthi 🖂
  

The above information outlines module CT5133: "Deep Learning" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

OptionalCT5105: Tools and Techniques for Large Scale Data Analytics

CT5105: Tools and Techniques for Large Scale Data Analytics

Semester 1 | Credits: 5

Large-scale data analytics is concerned with the processing and analysis of large quantities of data, typically from distributed sources (such as data streams on the internet). This module introduces students to state-of-the-art approaches to large-scale data analytics. Students learn about foundational concepts, software tools and advanced programming techniques for the scalable storage, processing and analysis of high- volume and high-velocity data, and how to apply them to practical problems. ** This module uses Java as programming language. Knowledge of Java is a prerequisite for participation in this module. ** Planned topics include: Definition of large-scale computational data analytics; Overview of approaches to the processing and analysis of high volume and high velocity data from distributed sources; Applications of large-scale data analytics; Foundations of cluster computing and parallel data processing; Introduction of selected relevant frameworks (e.g., Apache Hadoop and Spark). MapReduce; Advanced programming concepts for large-scale data analytics; Concepts and tools for large-scale data storage; Stream data analytics; Event Processing; Techniques and open-source tools for large-scale analytics; Computational statistics and machine learning with large-scale data processing frameworks such as Spark. Columnar data storage.
(Language of instruction: English)

Learning Outcomes

1. Be able to define large-scale data analytics and understand its characteristics
2. Be able to explain and apply concepts and tools for distributed and parallel processing of large-scale data
3. Know how to explain and apply concepts and tools for highly scalable storage, querying, filtering, sorting and synthesizing of data
4. Know how to describe and apply selected statistical and machine learning techniques and tools for the analysis of large-scale data
5. Know how to explain and apply approaches to stream data analytics and event processing

Assessments

• Written Assessment (70%)
• Continuous Assessment (30%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  MATTHIAS NICKLES 🖂
  
•  DEIRDRE KING 🖂
  
•  GERALDINE HEALY 🖂
  

Reading List

1. "Learning Spark: Lightning-Fast Big Data Analytics." by Holden Karau, Andy Konwinski, Patrick Wendell, Matei Zaharia
   Publisher: O'Reilly
2. "Hadoop: The Definitive Guide" by Tom White
   ISBN: 9781449311520.
   Publisher: "O'Reilly Media, Inc."
3. "Large-Scale Data Analytics" by Aris Gkoulalas-Divanis,Abderrahim Labbi
   ISBN: 1461492424.
   Publisher: Springer Science & Business Media

The above information outlines module CT5105: "Tools and Techniques for Large Scale Data Analytics" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

OptionalCT561: Systems Modelling and Simulation

CT561: Systems Modelling and Simulation

Semester 1 | Credits: 5

Simulation is a quantitative method used to support decision making and predicting system behaviour over time. This course focuses the system dynamics approach. The course covers the fundamentals of simulation, and describes how to design and build mathematical models. Case studies used include: software project management, public health policy planning, and capacity planning.
(Language of instruction: English)

Learning Outcomes

1. Define the aim of Simulation and its role in the decision making process for complex systems
2. Distinguish between the two feedback types: positive and negative
3. Demonstrate how to apply the system dynamics approach to areas including public health, software engineering management and capacity planning.
4. Explain and apply numerical integration methods to solve simulation problems.
5. Given a simulation problem, formulate a model, test the structure and equations, and perform detailed sensitivity analysis on the impact of a range of policy options
6. Build, test and evaluate models using Vensim.
7. Appreciate the differences between continuous and agent-based simulation

Assessments

• Written Assessment (70%)
• Continuous Assessment (30%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  JAMES DUGGAN 🖂
  
•  DEIRDRE KING 🖂
  
•  GERALDINE HEALY 🖂
  

The above information outlines module CT561: "Systems Modelling and Simulation" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

OptionalCT5141: Optimisation

CT5141: Optimisation

Semester 1 | Credits: 5

This module covers optimisation -- "the science of better". Optimisation is used in a huge variety of applications, including: finding time-saving transport routes; scheduling exams without conflicts; reducing weight and cost in engineering design; designing portfolios of financial investments; finding numerical data models with low expected error; and many more. In this module we will aim to understanding a broad range of applications and a unifying view of the field, including four main types of methods: (1) exact methods for constrained optimisation (2) constructive heuristics (3) gradient descent (briefly) (4) metaheuristics. We will use labs for practical implementations, writing our own optimisation programs from scratch in Python and also using state-of-the-art libraries.
(Language of instruction: English)

Learning Outcomes

1. Compare and contrast different algorithms and algorithm types (metaheuristics, constrained optimisation, gradient descent, constructive heuristics) and state their advantages and disadvantages for specific problems
2. State common real-world applications of optimisation algorithms
3. Implement a variety of metaheuristic algorithms, linear programming / constrained optimisation algorithms, and constructive heuristics, either from scratch or using library code, and interpret outcomes in a business or science application context
4. Design novel algorithms or algorithm varieties to suit specific problems

Assessments

• Written Assessment (70%)
• Continuous Assessment (30%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  ENDA BARRETT 🖂
  
•  JAMES MCDERMOTT 🖂
  

Reading List

1. "Essentials of Metaheuristics" by Sean Luke
2. "Programming Collective Intelligence" by Toby Segaran

The above information outlines module CT5141: "Optimisation" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

OptionalCT5121: Advanced Topics in Natural Language Processing

CT5121: Advanced Topics in Natural Language Processing

Semester 2 | Credits: 5

Advanced topics in natural language processing, including deep learning for NLP, machine translation and language resources. This module covers topics in the following areas: * Use of neural networks, deep learning and large language models for solving NLP tasks * Advanced NLP techniques including textual similarity, event extraction and question answering. * Multilingual and mulitmodal NLP techniques including machine translation * Applications of NLP in digital humanities, legal NLP, language learning or other similar areas
(Language of instruction: English)

Learning Outcomes

1. Use deep learning, neural networks and large language models for NLP
2. Synthesize practical knowledge of NLP to complex tasks in data analytics.
3. Apply multilingual NLP and build simple machine translation systems.
4. Create complex solutions for real world problems using NLP technologies
5. Solve novel NLP challenges using deep learning technologies

Assessments

• Written Assessment (50%)
• Continuous Assessment (50%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  DEIRDRE KING 🖂
  
•  PETER PAUL BUITELAAR 🖂
  
•  GERALDINE HEALY 🖂
  
•  John McCrae 🖂
  

The above information outlines module CT5121: "Advanced Topics in Natural Language Processing" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

OptionalEE551: Embedded Image Processing

EE551: Embedded Image Processing

Semester 1 | Credits: 5

Content: This module covers the concepts and technology that are central to embedded image processing. The course material is supported by practical examples and laboratories/assignments using Python software. Pre-requisites: (1) Knowledge of signal and system analysis including Fourier analysis and filtering. Knowledge of matrix algebra. (2) Knowledge of Python would be an advantage.
(Language of instruction: English)

Learning Outcomes

1. Describe a digital image in terms of the image parameters, sensor characteristics, and colour space.
2. Perform low-level operations (histogram processing, basic pixel-level processing) for image processing functions
3. Design and apply appropriate spatial domain filters for image processing tasks, e.g. noise removal.
4. Describe and apply frequency domain filtering techniques to digital images.
5. Apply shape analysis and segmentation algorithms to digital images.
6. Develop and apply feature detection algorithms to digital images.
7. Develop a complex object detection system for digital images.

Assessments

• Continuous Assessment (100%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  EDWARD JONES 🖂
  

Reading List

1. "Digital Image Processing" by Rafael Gonzalez and Richard Woods
   Publisher: Pearson
2. "Computer Vision: Algorithms and Applications" by Richard Szeliski
   Publisher: Springer

The above information outlines module EE551: "Embedded Image Processing" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

OptionalCT5113: Web and Network Science

CT5113: Web and Network Science

Semester 2 | Credits: 5

Web and Network Science is concerned with techniques and technologies for analysing, modelling and learning from data that is represented as a graph. The module takes a practical approach to the analysis and modelling of large network data sets from multiple domains. Students will learn the fundamentals of graph theory and how to apply graph analysis, modelling and evaluation techniques to real data sets for applications such as recommendation, authority ranking, link-prediction and community detection. The practical work in this module is done using the R programming language - and learners are expected to be able to programme in R.
(Language of instruction: English)

Learning Outcomes

1. Explain and discuss the theoretical principles behind graph analysis and modelling
2. pre-process, load and analyse data in a variety of network formats and standards
3. measure the fundamental properties of a graph
4. apply fundamentals of comparative network modelling to real data sets
5. apply the principles and techniques of graph partitioning, community-finding and modularity analysis to real network data
6. apply the core techniques in social network analysis to analyse a real social graph
7. apply graph analytical techniques to applications such as recommender systems, user role analysis and link prediction
8. visualise network data, where appropriate

Assessments

• Written Assessment (50%)
• Continuous Assessment (50%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  DEIRDRE KING 🖂
  
•  CONOR HAYES 🖂
  
•  GERALDINE HEALY 🖂
  

Reading List

1. "Networks" by Mark Newman
   Publisher: Oxford
2. "Statistical Analysis of Network Data with R" by Eric D. D. Kolaczyk ; Gábor Csárdi
   ISBN: 978-149390982.
   Publisher: Springer

The above information outlines module CT5113: "Web and Network Science" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

OptionalCT5187: Knowledge Representation

CT5187: Knowledge Representation

Semester 2 | Credits: 5

This module introduces students to Knowledge Representation (KR) and reasoning using formal logic. Planned topics include: Foundations of knowledge representation. Propositional and first-order logic (FOL). Foundations of reasoning. Logic programming. Satisfiability Solving (SAT) and Answer Set Programming (ASP). Probabilistic logics and uncertainty reasoning. Basics of machine learning in the context of KR.
(Language of instruction: English)

Learning Outcomes

1. Explain the fundamental principles of knowledge representation and reasoning
2. Describe and use syntax and semantics of important formal logics
3. Explain and be able to use fundamental types of reasoning and logic frameworks
4. Model application domains using logic languages and relational knowledge representation formats
5. Explain and apply selected Machine Learning models in the context of knowledge representation and reasoning

Assessments

• Written Assessment (70%)
• Continuous Assessment (30%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  MATTHIAS NICKLES 🖂
  
•  DEIRDRE KING 🖂
  
•  GERALDINE HEALY 🖂
  

Reading List

1. "Knowledge Representation and Reasoning" by Ronald J. Brachman, Hector J. Levesque
   Publisher: Elsevier/Morgan Kaufmann

The above information outlines module CT5187: "Knowledge Representation" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

OptionalCT5166: Knowledge Graphs

CT5166: Knowledge Graphs

Semester 2 | Credits: 5

Knowledge graphs are a fundamental part of many enterprise systems and this module will teach the fundamentals for working with knowledge graphs. This will focus on how knowledge graphs can be applied in enterprise and students will learn about the data models for knowledge graphs (including semantic web standards such as RDF), reasoning over knowledge graphs, linked open data, knowledge graphs in enterprise, knowledge graph extraction and knowledge graph linking. As such this module will teach the general principles of knowledge graphs alongside the technical tools used for these. This module will also build on techniques from artificial intelligence and natural language processing to show how automatic tools can create and manipulate knowledge graphs.
(Language of instruction: English)

Learning Outcomes

1. Explain how knowledge graphs can be used in enterprise
2. Model real-world knowledge as a graph and apply reasoning over this graph
3. Use standards such as RDF to represent a knowledge graph
4. Explain how knowledge graphs can be extracted from text and other sources
5. Be able to integrate knowledge graphs into real-world enterprise applications

Assessments

• Written Assessment (60%)
• Continuous Assessment (40%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  DEIRDRE KING 🖂
  
•  GERALDINE HEALY 🖂
  
•  John McCrae 🖂
  

Reading List

1. "Exploiting Linked Data and Knowledge Graphs for Large Organisations" by Jeff Z. Pan,Guido Vetere,Jose Manuel Gomez- Perez,Honghan Wu
   ISBN: 9783319456522.
   Publisher: Springer
2. "Knowledge Graphs" by Dieter Fensel,Umutcan Şimşek,Kevin Angele,Elwin Huaman,Elias Kärle,Oleksandra Panasiuk,Ioan Toma,Jürgen Umbrich,Alexander Wahler
   ISBN: 9783030374389.
   Publisher: Springer

The above information outlines module CT5166: "Knowledge Graphs" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.

OptionalCT5100: Data Visualisation

CT5100: Data Visualisation

Semester 2 | Credits: 5

Visualisation is a fundamental technique in presenting the properties of data and the results and evaluation of data analytical processes. For a data visualisation to be successful the analyst needs to have considered the properties of the data, the information to be communicated, the mode of visualisation delivery and the expectations of the audience. This module takes a practical approach to introducing learners to the strengths and weaknesses of human perception, and the use of best practices to represent complex and large data stories using visual primitives. The module demonstrates the role of visualisation in exploratory data analysis and its fundamental role in explaining data analytical outcomes. The module emphasises the need to communicate clearly, while adhering to the ethical requirement to present data-derived information truthfully and without bias. The examples covered during the module have been generated using the R language. However, students can use other languages and visualisation applications in their assignment work.
(Language of instruction: English)

Learning Outcomes

1. Describe the basic design principles underlying human perception, color theory and narrative
2. Analyse the effectiveness of different visual elements in communicating analytical information
3. Select the best visualisation strategy to use for different exploratory and explanatory scenarios
4. Execute different types of data visualisations for use in various exploratory and explanatory scenarios
5. Carry out basic data preprocessing and wrangling necessary to produce effective visualisations
6. Discuss the ethical issues of representing data and information truthfully when creating a visualisation
7. Critically evaluate data visualisations produced by other people

Assessments

• Written Assessment (65%)
• Continuous Assessment (35%)

Teachers & Administrators

Click a name to search for their researcher profile. Note: Only teachers publish research profiles.

•  DEIRDRE KING 🖂
  
•  CONOR HAYES 🖂
  
•  GERALDINE HEALY 🖂
  

Reading List

1. "R Graphics Cookbook" by Winston Chang
   Publisher: O'Reilly
2. "ggplot2" by Hadley Wickham
   ISBN: 9783319242750.
   Publisher: Springer
3. "Information Visualization" by Colin Ware
   ISBN: 9780123814647.
   Publisher: Elsevier
4. "Now You See it" by Stephen Few
   ISBN: 9780970601988.
   Publisher: Analytical Press
5. "The Visual Display of Quantitative Information" by Edward R. Tufte
   ISBN: 9781930824133.
   Publisher: Graphics Press

The above information outlines module CT5100: "Data Visualisation" and is valid from 2024 onwards.
Note: Module offerings and details may be subject to change.