MSc — 2025 entry Computer Vision, Robotics and Machine Learning

Expected prior learning: Knowledge of basic properties of signals and related methods, including Fourier series, Fourier transforms, Laplace transforms, and convolution. BEng/MEng students might have acquired this through study of module EEE2035 Engineering Mathematics III and/or module EEE2033 Circuits, Control and Communications. MSc students might have acquired this through study of an undergraduate module on “Signals and Systems” or through independent study. Module purpose: This introductory course in Digital Signal Processing explores mathematical tools used to represent, analyse and design basic DSP systems. This module underpins many key areas of digital systems, including audio-visual technology, digital communications, control systems, and computer vision. This topic is therefore of paramount importance to any electronic engineer. This module EEE3008 provides the expected prior learning for the following module EEEM030 Speech & Audio Processing and Recognition Taking module EEE3008 may also contribute to a deeper understanding of the following modules EEE3032 Computer Vision and Pattern Recognition, EEE3042 Audio and Video Processing and EEEM071 Advanced Topics in Computer Vision and Deep Learning

Expected prior learning:  None specifically advised. Module purpose:  Earth and planetary observation with remote sensing data is playing a key role in the present understanding of natural phenomena, prevention of disasters, resources monitoring, comprehension of origins of life. Through a series of lectures, seminars, open discussions and “thinking breaks” in class, the module aims to give an introduction to the scientific principles of remote sensing – both passive and active – as carried out by spacecraft. Remote sensing is discussed in terms of instrumentation, missions, products and applications. IMPORTANT: The Second assessment pattern (Written Exam) is only applicable to the MSc Short Course Students.

Expected prior learning: Module EEE2041 – Computer Vision & Graphics, or equivalent learning about the geometric interpretation of Linear Algebra (e.g. homogeneous coordinates and matrices for point transformation e.g. rotation, translation, scaling). Module purpose: The module delivers a grounding in Computer Vision, suitable for students with a grounding in linear algebra similar to that provided by EEE2041 – Computer Vision & Graphics) and will help with modules such EEEM071 Advanced Topics in Computer Vision and Deep Learning. Content is presented as an application-focused tour of Computer Vision from the low-level (image processing), through to high level model fitting and object recognition.  

Medical robotics is a rapidly developing industry that is vital to healthcare systems seeking better outcomes at reduced overall cost. This module introduces students to the workings of robots and how this is applied in solving both surgical and broader healthcare challenges. Students learn through lectures, practical sessions, tutorials and seminars requiring engagement with scientific literature. Case studies are a critical part of the module. These are industrially or research-based and require students to think about clinical conditions, ethical considerations and a range of attitudes to healthcare.The unit of assessment requires students to develop an understanding of the general theory behind robotics and identify the particularities applying to medical robots. The unit of assessment will also address the wider issues associated with medical robotics and their application. Practical sessions enable students to work with each other to solve problems and demonstrate the theoretical components of the module. An overarching series of lectures delivers critical technical information and links students¿ learning with case-studies to illustrate mechanical and medical issues. Seminars complement lectures and are designed for students to critically analyse, discuss and focus on particular aspects of medical robotic research in the scientific literature.

Module purpose: Advances related to energy efficiency issues and cost reductions have resulted in the rapid growth and deployment of networked devices and sensing/actuation systems that connect the physical world with the cyber world. This evolving framework, now recognized as the Artificial Intelligence of Things (AIoT), integrates IoT technologies with artificial intelligence (AI) to enhance automation, intelligence, and decision-making. AIoT incorporates several cutting-edge technologies, including wireless sensor networks, pervasive systems, ambient intelligence, context awareness, distributed systems, and machine learning-driven analytics. Module Overview: The advanced AIoT module is designed to provide a comprehensive understanding of how machine communications , coupled with AI, contribute to creating smart artificial intelligence-driven environments, focusing on networking and communication systems. The module provides an overview of the key concepts and enabling technologies for AIoT. It encompasses a cross-layer approach, allowing students to explore the practical aspects of sensors, actuators, and mainly communication systems for AIoT across physical, media access, and network layers. This includes security considerations, satellite AIoT, positioning and tracking for industrial applications, AIoT Platforms (Hardware, Software), protocols and standards (e.g. 6LowPAN, ZigBee, CoAp), semantic technologies, and data and information processing mechanisms. Also, the module explores AI-driven methodologies such as ensemble learning, multi-armed bandits for sequential decision-making, and lightweight machine learning Mmodels for AIoT applications. These techniques enhance real-time data analysis, predictive maintenance, anomaly detection, and adaptive control while ensuring computational efficiency.

This module introduces students to some of the basic ideas and concepts that underlie the development of artificially intelligent machine systems. Teaches core AI materials for problem solving (search, logic, probabilistic methods, Perceptrons as the building block for ANNs) Focuses on core understanding and problem solving: suitable tools/methods for a problem using problem classes Provides a clear understanding of neural networks, back-propagation, RBFs, ANN learning and optimisation Provides a clear understanding of intelligent agents via search methods and introducing cost functions Provides a clear understanding of Bayes’ Rule, conditional probability and uncertainty reasoning Provides a clear understanding of knowledge capture, symbolic knowledge representation and logical reasoning from antiquity to Boule to first order predicate rules and representations. Provides opportunity to implement concepts during coursework.

Machine/Deep learning has emerged from computer science and artificial intelligence. It draws on methods from a variety of related subjects including statistics, applied mathematics and more specialized fields, such as pattern recognition and neural network computation. This module offers the theory and related applications of advanced deep/machine learning topics and an overview their applications to other fields, such as natural language processing, medical imaging, health, audio, and fintech etc. The deep learning algorithms which will be studied are used widely in industry by AI start-ups to AI tech giants, like, Google, Meta, Microsoft, Amazon, Tesla etc. It provides a background and related theory of deep/machine learning to manipulate data from various domains like image, video, text, audio etc. This is done by various machine learning algorithms that are discussed, implemented, and demonstrated within the module.

This module will demonstrate fundamental concepts from the field of Natural Language Processing (NLP) and Computational Linguistics. It will also discuss some of the latest advances in NLP and Generative Artificial Intelligence with a focus on Language Models like BERT, T5, and GPT, and get student up to speed with current research. It will provide the necessary skills to enable students to build computational models for solving a range of problems, such as text classification, sequence classification, machine translation and building conversation agents. The students will learn how to build NLP pipelines for preparing training data and choosing appropriate algorithms and techniques to build such models. The module also focuses on aspects of ethical and trustworthy artificial intelligence with discussion on rigorous model evaluation and ethical considerations for computational modeling. Although traditional linguistic approaches will be mentioned, majority emphasis will be put on the state-of-the-art Deep Learning algorithms and Transfer Learning methods for building efficient and trustworthy NLP solutions. 

Expected prior learning: Knowledge of basic properties of signals and related methods, including Fourier series, Fourier transforms, Laplace transforms, and convolution. BEng/MEng students might have acquired this through study of module EEE2035 Engineering Mathematics III and/or module EEE2033 Circuits, Control and Communications. MSc students might have acquired this through study of an undergraduate module on “Signals and Systems” or through independent study. Module purpose: This introductory course in Digital Signal Processing explores mathematical tools used to represent, analyse and design basic DSP systems. This module underpins many key areas of digital systems, including audio-visual technology, digital communications, control systems, and computer vision. This topic is therefore of paramount importance to any electronic engineer. This module EEE3008 provides the expected prior learning for the following module EEEM030 Speech & Audio Processing and Recognition Taking module EEE3008 may also contribute to a deeper understanding of the following modules EEE3032 Computer Vision and Pattern Recognition, EEE3042 Audio and Video Processing and EEEM071 Advanced Topics in Computer Vision and Deep Learning

Expected prior learning:  None specifically advised. Module purpose:  Earth and planetary observation with remote sensing data is playing a key role in the present understanding of natural phenomena, prevention of disasters, resources monitoring, comprehension of origins of life. Through a series of lectures, seminars, open discussions and “thinking breaks” in class, the module aims to give an introduction to the scientific principles of remote sensing – both passive and active – as carried out by spacecraft. Remote sensing is discussed in terms of instrumentation, missions, products and applications. IMPORTANT: The Second assessment pattern (Written Exam) is only applicable to the MSc Short Course Students.

Expected prior learning: Module EEE2041 – Computer Vision & Graphics, or equivalent learning about the geometric interpretation of Linear Algebra (e.g. homogeneous coordinates and matrices for point transformation e.g. rotation, translation, scaling). Module purpose: The module delivers a grounding in Computer Vision, suitable for students with a grounding in linear algebra similar to that provided by EEE2041 – Computer Vision & Graphics) and will help with modules such EEEM071 Advanced Topics in Computer Vision and Deep Learning. Content is presented as an application-focused tour of Computer Vision from the low-level (image processing), through to high level model fitting and object recognition.  

Medical robotics is a rapidly developing industry that is vital to healthcare systems seeking better outcomes at reduced overall cost. This module introduces students to the workings of robots and how this is applied in solving both surgical and broader healthcare challenges. Students learn through lectures, practical sessions, tutorials and seminars requiring engagement with scientific literature. Case studies are a critical part of the module. These are industrially or research-based and require students to think about clinical conditions, ethical considerations and a range of attitudes to healthcare.The unit of assessment requires students to develop an understanding of the general theory behind robotics and identify the particularities applying to medical robots. The unit of assessment will also address the wider issues associated with medical robotics and their application. Practical sessions enable students to work with each other to solve problems and demonstrate the theoretical components of the module. An overarching series of lectures delivers critical technical information and links students¿ learning with case-studies to illustrate mechanical and medical issues. Seminars complement lectures and are designed for students to critically analyse, discuss and focus on particular aspects of medical robotic research in the scientific literature.

Module purpose: Advances related to energy efficiency issues and cost reductions have resulted in the rapid growth and deployment of networked devices and sensing/actuation systems that connect the physical world with the cyber world. This evolving framework, now recognized as the Artificial Intelligence of Things (AIoT), integrates IoT technologies with artificial intelligence (AI) to enhance automation, intelligence, and decision-making. AIoT incorporates several cutting-edge technologies, including wireless sensor networks, pervasive systems, ambient intelligence, context awareness, distributed systems, and machine learning-driven analytics. Module Overview: The advanced AIoT module is designed to provide a comprehensive understanding of how machine communications , coupled with AI, contribute to creating smart artificial intelligence-driven environments, focusing on networking and communication systems. The module provides an overview of the key concepts and enabling technologies for AIoT. It encompasses a cross-layer approach, allowing students to explore the practical aspects of sensors, actuators, and mainly communication systems for AIoT across physical, media access, and network layers. This includes security considerations, satellite AIoT, positioning and tracking for industrial applications, AIoT Platforms (Hardware, Software), protocols and standards (e.g. 6LowPAN, ZigBee, CoAp), semantic technologies, and data and information processing mechanisms. Also, the module explores AI-driven methodologies such as ensemble learning, multi-armed bandits for sequential decision-making, and lightweight machine learning Mmodels for AIoT applications. These techniques enhance real-time data analysis, predictive maintenance, anomaly detection, and adaptive control while ensuring computational efficiency.

This module introduces students to some of the basic ideas and concepts that underlie the development of artificially intelligent machine systems. Teaches core AI materials for problem solving (search, logic, probabilistic methods, Perceptrons as the building block for ANNs) Focuses on core understanding and problem solving: suitable tools/methods for a problem using problem classes Provides a clear understanding of neural networks, back-propagation, RBFs, ANN learning and optimisation Provides a clear understanding of intelligent agents via search methods and introducing cost functions Provides a clear understanding of Bayes’ Rule, conditional probability and uncertainty reasoning Provides a clear understanding of knowledge capture, symbolic knowledge representation and logical reasoning from antiquity to Boule to first order predicate rules and representations. Provides opportunity to implement concepts during coursework.

Machine/Deep learning has emerged from computer science and artificial intelligence. It draws on methods from a variety of related subjects including statistics, applied mathematics and more specialized fields, such as pattern recognition and neural network computation. This module offers the theory and related applications of advanced deep/machine learning topics and an overview their applications to other fields, such as natural language processing, medical imaging, health, audio, and fintech etc. The deep learning algorithms which will be studied are used widely in industry by AI start-ups to AI tech giants, like, Google, Meta, Microsoft, Amazon, Tesla etc. It provides a background and related theory of deep/machine learning to manipulate data from various domains like image, video, text, audio etc. This is done by various machine learning algorithms that are discussed, implemented, and demonstrated within the module.

This module will demonstrate fundamental concepts from the field of Natural Language Processing (NLP) and Computational Linguistics. It will also discuss some of the latest advances in NLP and Generative Artificial Intelligence with a focus on Language Models like BERT, T5, and GPT, and get student up to speed with current research. It will provide the necessary skills to enable students to build computational models for solving a range of problems, such as text classification, sequence classification, machine translation and building conversation agents. The students will learn how to build NLP pipelines for preparing training data and choosing appropriate algorithms and techniques to build such models. The module also focuses on aspects of ethical and trustworthy artificial intelligence with discussion on rigorous model evaluation and ethical considerations for computational modeling. Although traditional linguistic approaches will be mentioned, majority emphasis will be put on the state-of-the-art Deep Learning algorithms and Transfer Learning methods for building efficient and trustworthy NLP solutions. 

Expected prior learning: Knowledge of basic properties of signals and related methods, including Fourier series, Fourier transforms, Laplace transforms, and convolution. BEng/MEng students might have acquired this through study of module EEE2035 Engineering Mathematics III and/or module EEE2033 Circuits, Control and Communications. MSc students might have acquired this through study of an undergraduate module on “Signals and Systems” or through independent study. Module purpose: This introductory course in Digital Signal Processing explores mathematical tools used to represent, analyse and design basic DSP systems. This module underpins many key areas of digital systems, including audio-visual technology, digital communications, control systems, and computer vision. This topic is therefore of paramount importance to any electronic engineer. This module EEE3008 provides the expected prior learning for the following module EEEM030 Speech & Audio Processing and Recognition Taking module EEE3008 may also contribute to a deeper understanding of the following modules EEE3032 Computer Vision and Pattern Recognition, EEE3042 Audio and Video Processing and EEEM071 Advanced Topics in Computer Vision and Deep Learning

Expected prior learning:  None specifically advised. Module purpose:  Earth and planetary observation with remote sensing data is playing a key role in the present understanding of natural phenomena, prevention of disasters, resources monitoring, comprehension of origins of life. Through a series of lectures, seminars, open discussions and “thinking breaks” in class, the module aims to give an introduction to the scientific principles of remote sensing – both passive and active – as carried out by spacecraft. Remote sensing is discussed in terms of instrumentation, missions, products and applications. IMPORTANT: The Second assessment pattern (Written Exam) is only applicable to the MSc Short Course Students.

Expected prior learning: Module EEE2041 – Computer Vision & Graphics, or equivalent learning about the geometric interpretation of Linear Algebra (e.g. homogeneous coordinates and matrices for point transformation e.g. rotation, translation, scaling). Module purpose: The module delivers a grounding in Computer Vision, suitable for students with a grounding in linear algebra similar to that provided by EEE2041 – Computer Vision & Graphics) and will help with modules such EEEM071 Advanced Topics in Computer Vision and Deep Learning. Content is presented as an application-focused tour of Computer Vision from the low-level (image processing), through to high level model fitting and object recognition.  

Medical robotics is a rapidly developing industry that is vital to healthcare systems seeking better outcomes at reduced overall cost. This module introduces students to the workings of robots and how this is applied in solving both surgical and broader healthcare challenges. Students learn through lectures, practical sessions, tutorials and seminars requiring engagement with scientific literature. Case studies are a critical part of the module. These are industrially or research-based and require students to think about clinical conditions, ethical considerations and a range of attitudes to healthcare.The unit of assessment requires students to develop an understanding of the general theory behind robotics and identify the particularities applying to medical robots. The unit of assessment will also address the wider issues associated with medical robotics and their application. Practical sessions enable students to work with each other to solve problems and demonstrate the theoretical components of the module. An overarching series of lectures delivers critical technical information and links students¿ learning with case-studies to illustrate mechanical and medical issues. Seminars complement lectures and are designed for students to critically analyse, discuss and focus on particular aspects of medical robotic research in the scientific literature.

Module purpose: Advances related to energy efficiency issues and cost reductions have resulted in the rapid growth and deployment of networked devices and sensing/actuation systems that connect the physical world with the cyber world. This evolving framework, now recognized as the Artificial Intelligence of Things (AIoT), integrates IoT technologies with artificial intelligence (AI) to enhance automation, intelligence, and decision-making. AIoT incorporates several cutting-edge technologies, including wireless sensor networks, pervasive systems, ambient intelligence, context awareness, distributed systems, and machine learning-driven analytics. Module Overview: The advanced AIoT module is designed to provide a comprehensive understanding of how machine communications , coupled with AI, contribute to creating smart artificial intelligence-driven environments, focusing on networking and communication systems. The module provides an overview of the key concepts and enabling technologies for AIoT. It encompasses a cross-layer approach, allowing students to explore the practical aspects of sensors, actuators, and mainly communication systems for AIoT across physical, media access, and network layers. This includes security considerations, satellite AIoT, positioning and tracking for industrial applications, AIoT Platforms (Hardware, Software), protocols and standards (e.g. 6LowPAN, ZigBee, CoAp), semantic technologies, and data and information processing mechanisms. Also, the module explores AI-driven methodologies such as ensemble learning, multi-armed bandits for sequential decision-making, and lightweight machine learning Mmodels for AIoT applications. These techniques enhance real-time data analysis, predictive maintenance, anomaly detection, and adaptive control while ensuring computational efficiency.

This module introduces students to some of the basic ideas and concepts that underlie the development of artificially intelligent machine systems. Teaches core AI materials for problem solving (search, logic, probabilistic methods, Perceptrons as the building block for ANNs) Focuses on core understanding and problem solving: suitable tools/methods for a problem using problem classes Provides a clear understanding of neural networks, back-propagation, RBFs, ANN learning and optimisation Provides a clear understanding of intelligent agents via search methods and introducing cost functions Provides a clear understanding of Bayes’ Rule, conditional probability and uncertainty reasoning Provides a clear understanding of knowledge capture, symbolic knowledge representation and logical reasoning from antiquity to Boule to first order predicate rules and representations. Provides opportunity to implement concepts during coursework.

Machine/Deep learning has emerged from computer science and artificial intelligence. It draws on methods from a variety of related subjects including statistics, applied mathematics and more specialized fields, such as pattern recognition and neural network computation. This module offers the theory and related applications of advanced deep/machine learning topics and an overview their applications to other fields, such as natural language processing, medical imaging, health, audio, and fintech etc. The deep learning algorithms which will be studied are used widely in industry by AI start-ups to AI tech giants, like, Google, Meta, Microsoft, Amazon, Tesla etc. It provides a background and related theory of deep/machine learning to manipulate data from various domains like image, video, text, audio etc. This is done by various machine learning algorithms that are discussed, implemented, and demonstrated within the module.

This module will demonstrate fundamental concepts from the field of Natural Language Processing (NLP) and Computational Linguistics. It will also discuss some of the latest advances in NLP and Generative Artificial Intelligence with a focus on Language Models like BERT, T5, and GPT, and get student up to speed with current research. It will provide the necessary skills to enable students to build computational models for solving a range of problems, such as text classification, sequence classification, machine translation and building conversation agents. The students will learn how to build NLP pipelines for preparing training data and choosing appropriate algorithms and techniques to build such models. The module also focuses on aspects of ethical and trustworthy artificial intelligence with discussion on rigorous model evaluation and ethical considerations for computational modeling. Although traditional linguistic approaches will be mentioned, majority emphasis will be put on the state-of-the-art Deep Learning algorithms and Transfer Learning methods for building efficient and trustworthy NLP solutions. 

Expected prior learning: Knowledge of basic properties of signals and related methods, including Fourier series, Fourier transforms, Laplace transforms, and convolution. BEng/MEng students might have acquired this through study of module EEE2035 Engineering Mathematics III and/or module EEE2033 Circuits, Control and Communications. MSc students might have acquired this through study of an undergraduate module on “Signals and Systems” or through independent study. Module purpose: This introductory course in Digital Signal Processing explores mathematical tools used to represent, analyse and design basic DSP systems. This module underpins many key areas of digital systems, including audio-visual technology, digital communications, control systems, and computer vision. This topic is therefore of paramount importance to any electronic engineer. This module EEE3008 provides the expected prior learning for the following module EEEM030 Speech & Audio Processing and Recognition Taking module EEE3008 may also contribute to a deeper understanding of the following modules EEE3032 Computer Vision and Pattern Recognition, EEE3042 Audio and Video Processing and EEEM071 Advanced Topics in Computer Vision and Deep Learning

Expected prior learning:  None specifically advised. Module purpose:  Earth and planetary observation with remote sensing data is playing a key role in the present understanding of natural phenomena, prevention of disasters, resources monitoring, comprehension of origins of life. Through a series of lectures, seminars, open discussions and “thinking breaks” in class, the module aims to give an introduction to the scientific principles of remote sensing – both passive and active – as carried out by spacecraft. Remote sensing is discussed in terms of instrumentation, missions, products and applications. IMPORTANT: The Second assessment pattern (Written Exam) is only applicable to the MSc Short Course Students.

Expected prior learning: Module EEE2041 – Computer Vision & Graphics, or equivalent learning about the geometric interpretation of Linear Algebra (e.g. homogeneous coordinates and matrices for point transformation e.g. rotation, translation, scaling). Module purpose: The module delivers a grounding in Computer Vision, suitable for students with a grounding in linear algebra similar to that provided by EEE2041 – Computer Vision & Graphics) and will help with modules such EEEM071 Advanced Topics in Computer Vision and Deep Learning. Content is presented as an application-focused tour of Computer Vision from the low-level (image processing), through to high level model fitting and object recognition.  

Medical robotics is a rapidly developing industry that is vital to healthcare systems seeking better outcomes at reduced overall cost. This module introduces students to the workings of robots and how this is applied in solving both surgical and broader healthcare challenges. Students learn through lectures, practical sessions, tutorials and seminars requiring engagement with scientific literature. Case studies are a critical part of the module. These are industrially or research-based and require students to think about clinical conditions, ethical considerations and a range of attitudes to healthcare.The unit of assessment requires students to develop an understanding of the general theory behind robotics and identify the particularities applying to medical robots. The unit of assessment will also address the wider issues associated with medical robotics and their application. Practical sessions enable students to work with each other to solve problems and demonstrate the theoretical components of the module. An overarching series of lectures delivers critical technical information and links students¿ learning with case-studies to illustrate mechanical and medical issues. Seminars complement lectures and are designed for students to critically analyse, discuss and focus on particular aspects of medical robotic research in the scientific literature.

Module purpose: Advances related to energy efficiency issues and cost reductions have resulted in the rapid growth and deployment of networked devices and sensing/actuation systems that connect the physical world with the cyber world. This evolving framework, now recognized as the Artificial Intelligence of Things (AIoT), integrates IoT technologies with artificial intelligence (AI) to enhance automation, intelligence, and decision-making. AIoT incorporates several cutting-edge technologies, including wireless sensor networks, pervasive systems, ambient intelligence, context awareness, distributed systems, and machine learning-driven analytics. Module Overview: The advanced AIoT module is designed to provide a comprehensive understanding of how machine communications , coupled with AI, contribute to creating smart artificial intelligence-driven environments, focusing on networking and communication systems. The module provides an overview of the key concepts and enabling technologies for AIoT. It encompasses a cross-layer approach, allowing students to explore the practical aspects of sensors, actuators, and mainly communication systems for AIoT across physical, media access, and network layers. This includes security considerations, satellite AIoT, positioning and tracking for industrial applications, AIoT Platforms (Hardware, Software), protocols and standards (e.g. 6LowPAN, ZigBee, CoAp), semantic technologies, and data and information processing mechanisms. Also, the module explores AI-driven methodologies such as ensemble learning, multi-armed bandits for sequential decision-making, and lightweight machine learning Mmodels for AIoT applications. These techniques enhance real-time data analysis, predictive maintenance, anomaly detection, and adaptive control while ensuring computational efficiency.

This module introduces students to some of the basic ideas and concepts that underlie the development of artificially intelligent machine systems. Teaches core AI materials for problem solving (search, logic, probabilistic methods, Perceptrons as the building block for ANNs) Focuses on core understanding and problem solving: suitable tools/methods for a problem using problem classes Provides a clear understanding of neural networks, back-propagation, RBFs, ANN learning and optimisation Provides a clear understanding of intelligent agents via search methods and introducing cost functions Provides a clear understanding of Bayes’ Rule, conditional probability and uncertainty reasoning Provides a clear understanding of knowledge capture, symbolic knowledge representation and logical reasoning from antiquity to Boule to first order predicate rules and representations. Provides opportunity to implement concepts during coursework.

Machine/Deep learning has emerged from computer science and artificial intelligence. It draws on methods from a variety of related subjects including statistics, applied mathematics and more specialized fields, such as pattern recognition and neural network computation. This module offers the theory and related applications of advanced deep/machine learning topics and an overview their applications to other fields, such as natural language processing, medical imaging, health, audio, and fintech etc. The deep learning algorithms which will be studied are used widely in industry by AI start-ups to AI tech giants, like, Google, Meta, Microsoft, Amazon, Tesla etc. It provides a background and related theory of deep/machine learning to manipulate data from various domains like image, video, text, audio etc. This is done by various machine learning algorithms that are discussed, implemented, and demonstrated within the module.

This module will demonstrate fundamental concepts from the field of Natural Language Processing (NLP) and Computational Linguistics. It will also discuss some of the latest advances in NLP and Generative Artificial Intelligence with a focus on Language Models like BERT, T5, and GPT, and get student up to speed with current research. It will provide the necessary skills to enable students to build computational models for solving a range of problems, such as text classification, sequence classification, machine translation and building conversation agents. The students will learn how to build NLP pipelines for preparing training data and choosing appropriate algorithms and techniques to build such models. The module also focuses on aspects of ethical and trustworthy artificial intelligence with discussion on rigorous model evaluation and ethical considerations for computational modeling. Although traditional linguistic approaches will be mentioned, majority emphasis will be put on the state-of-the-art Deep Learning algorithms and Transfer Learning methods for building efficient and trustworthy NLP solutions.