Engineering Tripos Part IIB, 4F12: Computer Vision, 2018-19
Module Leader
Lecturers
Prof R Cipolla and Dr R Turner
Timing and Structure
Michaelmas term. 16 lectures (including 3 examples classes). Assessment: 100% exam
Aims
The aims of the course are to:
- introduce the principles, models and applications of computer vision.
- cover image structure, projection, stereo vision, structure from motion and object detection and recognition.
- give case studies of industrial (robotic) applications of computer vision, including visual navigation for autonomous robots, robot hand-eye coordination and novel man-machine interfaces.
Objectives
As specific objectives, by the end of the course students should be able to:
- design feature detectors to detect, localise and track image features.
- model perspective image formation and calibrate single and multiple camera systems.
- recover 3D position and shape information from arbitrary viewpoints;
- appreciate the problems in finding corresponding features in different viewpoints.
- analyse visual motion to recover scene structure and viewer motion, and understand how this information can be used in navigation;
- understand how simple object recognition systems can be designed so that they are independent of lighting and camera viewpoin.
- appreciate the industrial potential of computer vision but understand the limitations of current methods.
Content
- Introduction (1L)
Computer vision: what is it, why study it and how ? The eye and the camera, vision as an information processing task. A geometrical framework for vision. 3D interpretation of 2D images. Applications.
- Image structure (3L)
Image intensities and structure: edges, corners and blobs. Edge detection, the aperture problem. Corner and blob detection. Contour extraction using B-spline snakes. Texture. Feature descriptors and matching.
- Projection (3L)
Orthographic projection. Planar perspective projection. Vanishing points and lines. Projection matrix, homogeneous coordinates. Camera calibration, recovery of world position. Weak perspective and the affine camera. Projective invariants.
- Stereo vision and Structure from Motion (3L)
Epipolar geometry and the essential matrix. Recovery of depth. Uncalibrated cameras and the fundamental matrix. The correspondence problem. Structure from motion. 3D shape from multiple view stereo.
- Object detection and recognition (3L)
Basic target detection and tracking. Machine learning for object detection and recognition. Random decision forests, support vector machines and boosting. Deep learning with convolutional neural networks.
- Example classes (3L)
Discussion of examples papers and past examination papers.
Booklists
Please see the Booklist for Group F Courses for references for this module.
Examination Guidelines
Please refer to Form & conduct of the examinations.
UK-SPEC
This syllabus contributes to the following areas of the UK-SPEC standard:
Toggle display of UK-SPEC areas.
GT1
Develop transferable skills that will be of value in a wide range of situations. These are exemplified by the Qualifications and Curriculum Authority Higher Level Key Skills and include problem solving, communication, and working with others, as well as the effective use of general IT facilities and information retrieval skills. They also include planning self-learning and improving performance, as the foundation for lifelong learning/CPD.
IA1
Apply appropriate quantitative science and engineering tools to the analysis of problems.
IA2
Demonstrate creative and innovative ability in the synthesis of solutions and in formulating designs.
KU1
Demonstrate knowledge and understanding of essential facts, concepts, theories and principles of their engineering discipline, and its underpinning science and mathematics.
KU2
Have an appreciation of the wider multidisciplinary engineering context and its underlying principles.
D1
Wide knowledge and comprehensive understanding of design processes and methodologies and the ability to apply and adapt them in unfamiliar situations.
D4
Ability to generate an innovative design for products, systems, components or processes to fulfil new needs.
E1
Ability to use fundamental knowledge to investigate new and emerging technologies.
E2
Ability to extract data pertinent to an unfamiliar problem, and apply its solution using computer based engineering tools when appropriate.
E3
Ability to apply mathematical and computer based models for solving problems in engineering, and the ability to assess the limitations of particular cases.
P1
A thorough understanding of current practice and its limitations and some appreciation of likely new developments.
P3
Understanding of contexts in which engineering knowledge can be applied (e.g. operations and management, technology, development, etc).
US1
A comprehensive understanding of the scientific principles of own specialisation and related disciplines.
US2
A comprehensive knowledge and understanding of mathematical and computer models relevant to the engineering discipline, and an appreciation of their limitations.
US3
An understanding of concepts from a range of areas including some outside engineering, and the ability to apply them effectively in engineering projects.
US4
An awareness of developing technologies related to own specialisation.
Last modified: 17/05/2018 14:22
Engineering Tripos Part IIB, 4F12: Computer Vision, 2021-22
Module Leader
Lecturers
Timing and Structure
Michaelmas term. 16 lectures (including 3 examples classes). Assessment: 100% exam
Aims
The aims of the course are to:
- introduce the principles, models and applications of computer vision.
- cover image structure, projection, stereo vision, structure from motion and object detection and recognition.
- give case studies of industrial (robotic) applications of computer vision, including visual navigation for autonomous robots, robot hand-eye coordination and novel man-machine interfaces.
Objectives
As specific objectives, by the end of the course students should be able to:
- design feature detectors to detect, localise and track image features.
- model perspective image formation and calibrate single and multiple camera systems.
- recover 3D position and shape information from arbitrary viewpoints;
- appreciate the problems in finding corresponding features in different viewpoints.
- analyse visual motion to recover scene structure and viewer motion, and understand how this information can be used in navigation;
- understand how simple object recognition systems can be designed so that they are independent of lighting and camera viewpoint.
- appreciate the commerical and industrial potential of computer vision but understand the limitations of current methods.
Content
- Introduction (1L)
Computer vision: what is it, why study it and how ? The eye and the camera, vision as an information processing task. Geometrical and statistical frameworks for vision. 3D interpretation of 2D images. Applications.
- Image structure (3L)
Image intensities and structure: edges, corners and blobs. Edge detection, the aperture problem and corner detection. Image pyramids, blob detection with band-pass filtering. The SIFT feature descriptor for matching. Characterising textures.
- Projection (3L)
Orthographic projection. Planar perspective projection. Vanishing points and lines. Projection matrix, homogeneous coordinates. Camera calibration, recovery of world position. Weak perspective and the affine camera. Projective invariants.
- Stereo vision and Structure from Motion (2L)
Epipolar geometry and the essential matrix. Recovery of depth by triangulation. Uncalibrated cameras and the fundamental matrix. The correspondence problem. Structure from motion. 3D shape examples from multiple view stereo.
- Deep Learning for Computer Vision (4L)
Basic architectures for deep learning in computer vision. Object detection, classification and semantic segmentation. Object recognition, feature embedding and metric learning. Transformers, scaling laws for computer vision, neural architecture search. Self-supervised learning and pseudo-labelling.
- Example classes (3L)
Discussion of examples papers and past examination papers.
Booklists
Please refer to the Booklist for Part IIB Courses for references to this module, this can be found on the associated Moodle course.
Examination Guidelines
Please refer to Form & conduct of the examinations.
UK-SPEC
This syllabus contributes to the following areas of the UK-SPEC standard:
Toggle display of UK-SPEC areas.
GT1
Develop transferable skills that will be of value in a wide range of situations. These are exemplified by the Qualifications and Curriculum Authority Higher Level Key Skills and include problem solving, communication, and working with others, as well as the effective use of general IT facilities and information retrieval skills. They also include planning self-learning and improving performance, as the foundation for lifelong learning/CPD.
IA1
Apply appropriate quantitative science and engineering tools to the analysis of problems.
IA2
Demonstrate creative and innovative ability in the synthesis of solutions and in formulating designs.
KU1
Demonstrate knowledge and understanding of essential facts, concepts, theories and principles of their engineering discipline, and its underpinning science and mathematics.
KU2
Have an appreciation of the wider multidisciplinary engineering context and its underlying principles.
D1
Wide knowledge and comprehensive understanding of design processes and methodologies and the ability to apply and adapt them in unfamiliar situations.
D4
Ability to generate an innovative design for products, systems, components or processes to fulfil new needs.
E1
Ability to use fundamental knowledge to investigate new and emerging technologies.
E2
Ability to extract data pertinent to an unfamiliar problem, and apply its solution using computer based engineering tools when appropriate.
E3
Ability to apply mathematical and computer based models for solving problems in engineering, and the ability to assess the limitations of particular cases.
P1
A thorough understanding of current practice and its limitations and some appreciation of likely new developments.
P3
Understanding of contexts in which engineering knowledge can be applied (e.g. operations and management, technology, development, etc).
US1
A comprehensive understanding of the scientific principles of own specialisation and related disciplines.
US2
A comprehensive knowledge and understanding of mathematical and computer models relevant to the engineering discipline, and an appreciation of their limitations.
US3
An understanding of concepts from a range of areas including some outside engineering, and the ability to apply them effectively in engineering projects.
US4
An awareness of developing technologies related to own specialisation.
Last modified: 24/09/2021 16:40
Engineering Tripos Part IIB, 4F12: Computer Vision, 2019-20
Module Leader
Lecturers
Prof R Cipolla and Dr I Budvytis
Timing and Structure
Michaelmas term. 16 lectures (including 3 examples classes). Assessment: 100% exam
Aims
The aims of the course are to:
- introduce the principles, models and applications of computer vision.
- cover image structure, projection, stereo vision, structure from motion and object detection and recognition.
- give case studies of industrial (robotic) applications of computer vision, including visual navigation for autonomous robots, robot hand-eye coordination and novel man-machine interfaces.
Objectives
As specific objectives, by the end of the course students should be able to:
- design feature detectors to detect, localise and track image features.
- model perspective image formation and calibrate single and multiple camera systems.
- recover 3D position and shape information from arbitrary viewpoints;
- appreciate the problems in finding corresponding features in different viewpoints.
- analyse visual motion to recover scene structure and viewer motion, and understand how this information can be used in navigation;
- understand how simple object recognition systems can be designed so that they are independent of lighting and camera viewpoint.
- appreciate the commerical and industrial potential of computer vision but understand the limitations of current methods.
Content
- Introduction (1L)
Computer vision: what is it, why study it and how ? The eye and the camera, vision as an information processing task. A geometrical framework for vision. 3D interpretation of 2D images. Applications.
- Image structure (3L)
Image intensities and structure: edges, corners and blobs. Edge detection, the aperture problem. Corner and blob detection. Contour extraction using B-spline snakes. Texture. Feature descriptors and matching.
- Projection (3L)
Orthographic projection. Planar perspective projection. Vanishing points and lines. Projection matrix, homogeneous coordinates. Camera calibration, recovery of world position. Weak perspective and the affine camera. Projective invariants.
- Stereo vision and Structure from Motion (3L)
Epipolar geometry and the essential matrix. Recovery of depth. Uncalibrated cameras and the fundamental matrix. The correspondence problem. Structure from motion. 3D shape from multiple view stereo.
- Object detection and recognition (3L)
Basic architectures for deep learning in computer vision. Object detection, classification and semantic segmentation. Object recognition, feature embedding and metric learning. Reconstruction, localisation and structured deep learning.
- Example classes (3L)
Discussion of examples papers and past examination papers.
Booklists
Please see the Booklist for Group F Courses for references for this module.
Examination Guidelines
Please refer to Form & conduct of the examinations.
UK-SPEC
This syllabus contributes to the following areas of the UK-SPEC standard:
Toggle display of UK-SPEC areas.
GT1
Develop transferable skills that will be of value in a wide range of situations. These are exemplified by the Qualifications and Curriculum Authority Higher Level Key Skills and include problem solving, communication, and working with others, as well as the effective use of general IT facilities and information retrieval skills. They also include planning self-learning and improving performance, as the foundation for lifelong learning/CPD.
IA1
Apply appropriate quantitative science and engineering tools to the analysis of problems.
IA2
Demonstrate creative and innovative ability in the synthesis of solutions and in formulating designs.
KU1
Demonstrate knowledge and understanding of essential facts, concepts, theories and principles of their engineering discipline, and its underpinning science and mathematics.
KU2
Have an appreciation of the wider multidisciplinary engineering context and its underlying principles.
D1
Wide knowledge and comprehensive understanding of design processes and methodologies and the ability to apply and adapt them in unfamiliar situations.
D4
Ability to generate an innovative design for products, systems, components or processes to fulfil new needs.
E1
Ability to use fundamental knowledge to investigate new and emerging technologies.
E2
Ability to extract data pertinent to an unfamiliar problem, and apply its solution using computer based engineering tools when appropriate.
E3
Ability to apply mathematical and computer based models for solving problems in engineering, and the ability to assess the limitations of particular cases.
P1
A thorough understanding of current practice and its limitations and some appreciation of likely new developments.
P3
Understanding of contexts in which engineering knowledge can be applied (e.g. operations and management, technology, development, etc).
US1
A comprehensive understanding of the scientific principles of own specialisation and related disciplines.
US2
A comprehensive knowledge and understanding of mathematical and computer models relevant to the engineering discipline, and an appreciation of their limitations.
US3
An understanding of concepts from a range of areas including some outside engineering, and the ability to apply them effectively in engineering projects.
US4
An awareness of developing technologies related to own specialisation.
Last modified: 16/09/2019 16:49
Engineering Tripos Part IIB, 4F12: Computer Vision, 2022-23
Module Leader
Lecturers
Prof R Cipolla and Dr Ignas Budvytis
Timing and Structure
Michaelmas term. 16 lectures (including 3 examples classes). Assessment: 100% exam
Aims
The aims of the course are to:
- introduce the principles, models and applications of computer vision.
- cover image structure, projection, stereo vision, structure from motion and object detection and recognition.
- give case studies of industrial (robotic) applications of computer vision, including visual navigation for autonomous robots, robot hand-eye coordination and novel man-machine interfaces.
Objectives
As specific objectives, by the end of the course students should be able to:
- design feature detectors to detect, localise and track image features.
- model perspective image formation and calibrate single and multiple camera systems.
- recover 3D position and shape information from arbitrary viewpoints;
- appreciate the problems in finding corresponding features in different viewpoints.
- analyse visual motion to recover scene structure and viewer motion, and understand how this information can be used in navigation;
- understand how simple object recognition systems can be designed so that they are independent of lighting and camera viewpoint.
- appreciate the commerical and industrial potential of computer vision but understand its limitations.
Content
- Introduction (1L)
Computer vision: what is it, why study it and how ? The eye and the camera, vision as an information processing task. Geometrical and statistical frameworks for vision. 3D interpretation of 2D images. Applications.
- Image structure (4L)
Image intensities and structure: edges, corners and blobs. Edge detection, the aperture problem and corner detection. Image pyramids, blob detection with band-pass filtering. The SIFT feature descriptor for matching. Characterising textures.
- Projection (4L)
Orthographic projection. Planar perspective projection. Vanishing points and lines. Projection matrix, homogeneous coordinates. Camera calibration, recovery of world position. Weak perspective and the affine camera. Projective invariants.
- Stereo vision and Structure from Motion (2L)
Epipolar geometry and the essential matrix. Recovery of depth by triangulation. Uncalibrated cameras and the fundamental matrix. The correspondence problem. Structure from motion. 3D shape examples from multiple view stereo.
- Deep Learning for Computer Vision (5L)
Basic architectures for deep learning in computer vision. Object detection, classification and semantic segmentation. Object recognition, feature embedding and metric learning. Transformers for computer vision and self-supervised learning.
- Example classes
Discussion of examples papers and past examination papers will be integrated with lectures.
Booklists
Please refer to the Booklist for Part IIB Courses for references to this module, this can be found on the associated Moodle course.
Examination Guidelines
Please refer to Form & conduct of the examinations.
UK-SPEC
This syllabus contributes to the following areas of the UK-SPEC standard:
Toggle display of UK-SPEC areas.
GT1
Develop transferable skills that will be of value in a wide range of situations. These are exemplified by the Qualifications and Curriculum Authority Higher Level Key Skills and include problem solving, communication, and working with others, as well as the effective use of general IT facilities and information retrieval skills. They also include planning self-learning and improving performance, as the foundation for lifelong learning/CPD.
IA1
Apply appropriate quantitative science and engineering tools to the analysis of problems.
IA2
Demonstrate creative and innovative ability in the synthesis of solutions and in formulating designs.
KU1
Demonstrate knowledge and understanding of essential facts, concepts, theories and principles of their engineering discipline, and its underpinning science and mathematics.
KU2
Have an appreciation of the wider multidisciplinary engineering context and its underlying principles.
D1
Wide knowledge and comprehensive understanding of design processes and methodologies and the ability to apply and adapt them in unfamiliar situations.
D4
Ability to generate an innovative design for products, systems, components or processes to fulfil new needs.
E1
Ability to use fundamental knowledge to investigate new and emerging technologies.
E2
Ability to extract data pertinent to an unfamiliar problem, and apply its solution using computer based engineering tools when appropriate.
E3
Ability to apply mathematical and computer based models for solving problems in engineering, and the ability to assess the limitations of particular cases.
P1
A thorough understanding of current practice and its limitations and some appreciation of likely new developments.
P3
Understanding of contexts in which engineering knowledge can be applied (e.g. operations and management, technology, development, etc).
US1
A comprehensive understanding of the scientific principles of own specialisation and related disciplines.
US2
A comprehensive knowledge and understanding of mathematical and computer models relevant to the engineering discipline, and an appreciation of their limitations.
US3
An understanding of concepts from a range of areas including some outside engineering, and the ability to apply them effectively in engineering projects.
US4
An awareness of developing technologies related to own specialisation.
Last modified: 11/11/2022 12:19
Engineering Tripos Part IIB, 4F12: Computer Vision, 2017-18
Module Leader
Lecturers
Prof R Cipolla and Dr R Turner
Timing and Structure
Michaelmas term. 16 lectures (including 3 examples classes). Assessment: 100% exam
Aims
The aims of the course are to:
- introduce the principles, models and applications of computer vision.
- cover image structure, projection, stereo vision, structure from motion and object detection and recognition.
- give case studies of industrial (robotic) applications of computer vision, including visual navigation for autonomous robots, robot hand-eye coordination and novel man-machine interfaces.
Objectives
As specific objectives, by the end of the course students should be able to:
- design feature detectors to detect, localise and track image features.
- model perspective image formation and calibrate single and multiple camera systems.
- recover 3D position and shape information from arbitrary viewpoints;
- appreciate the problems in finding corresponding features in different viewpoints.
- analyse visual motion to recover scene structure and viewer motion, and understand how this information can be used in navigation;
- understand how simple object recognition systems can be designed so that they are independent of lighting and camera viewpoin.
- appreciate the industrial potential of computer vision but understand the limitations of current methods.
Content
- Introduction (1L)
Computer vision: what is it, why study it and how ? The eye and the camera, vision as an information processing task. A geometrical framework for vision. 3D interpretation of 2D images. Applications.
- Image structure (3L)
Image intensities and structure: edges, corners and blobs. Edge detection, the aperture problem. Corner and blob detection. Contour extraction using B-spline snakes. Texture. Feature descriptors and matching.
- Projection (3L)
Orthographic projection. Planar perspective projection. Vanishing points and lines. Projection matrix, homogeneous coordinates. Camera calibration, recovery of world position. Weak perspective and the affine camera. Projective invariants.
- Stereo vision and Structure from Motion (3L)
Epipolar geometry and the essential matrix. Recovery of depth. Uncalibrated cameras and the fundamental matrix. The correspondence problem. Structure from motion. 3D shape from multiple view stereo.
- Object detection and recognition (3L)
Basic target detection and tracking. Machine learning for object detection and recognition. Random decision forests, support vector machines and boosting. Deep learning with convolutional neural networks.
- Example classes (3L)
Discussion of examples papers and past examination papers.
Booklists
Please see the Booklist for Group F Courses for references for this module.
Examination Guidelines
Please refer to Form & conduct of the examinations.
UK-SPEC
This syllabus contributes to the following areas of the UK-SPEC standard:
Toggle display of UK-SPEC areas.
GT1
Develop transferable skills that will be of value in a wide range of situations. These are exemplified by the Qualifications and Curriculum Authority Higher Level Key Skills and include problem solving, communication, and working with others, as well as the effective use of general IT facilities and information retrieval skills. They also include planning self-learning and improving performance, as the foundation for lifelong learning/CPD.
IA1
Apply appropriate quantitative science and engineering tools to the analysis of problems.
IA2
Demonstrate creative and innovative ability in the synthesis of solutions and in formulating designs.
KU1
Demonstrate knowledge and understanding of essential facts, concepts, theories and principles of their engineering discipline, and its underpinning science and mathematics.
KU2
Have an appreciation of the wider multidisciplinary engineering context and its underlying principles.
D1
Wide knowledge and comprehensive understanding of design processes and methodologies and the ability to apply and adapt them in unfamiliar situations.
D4
Ability to generate an innovative design for products, systems, components or processes to fulfil new needs.
E1
Ability to use fundamental knowledge to investigate new and emerging technologies.
E2
Ability to extract data pertinent to an unfamiliar problem, and apply its solution using computer based engineering tools when appropriate.
E3
Ability to apply mathematical and computer based models for solving problems in engineering, and the ability to assess the limitations of particular cases.
P1
A thorough understanding of current practice and its limitations and some appreciation of likely new developments.
P3
Understanding of contexts in which engineering knowledge can be applied (e.g. operations and management, technology, development, etc).
US1
A comprehensive understanding of the scientific principles of own specialisation and related disciplines.
US2
A comprehensive knowledge and understanding of mathematical and computer models relevant to the engineering discipline, and an appreciation of their limitations.
US3
An understanding of concepts from a range of areas including some outside engineering, and the ability to apply them effectively in engineering projects.
US4
An awareness of developing technologies related to own specialisation.
Last modified: 31/05/2017 10:06
Engineering Tripos Part IIB, 4F12: Computer Vision, 2023-24
Module Leader
Lecturers
Prof R Cipolla and Dr S Albanie
Timing and Structure
Michaelmas term. 16 lectures (including 3 examples classes). Assessment: 100% exam
Aims
The aims of the course are to:
- introduce the principles, models and applications of computer vision.
- cover image structure, projection, stereo vision, structure from motion and object detection and recognition.
- give case studies of industrial (robotic) applications of computer vision, including visual navigation for autonomous robots, robot hand-eye coordination and novel man-machine interfaces.
Objectives
As specific objectives, by the end of the course students should be able to:
- design feature detectors to detect, localise and track image features.
- model perspective image formation and calibrate single and multiple camera systems.
- recover 3D position and shape information from arbitrary viewpoints;
- appreciate the problems in finding corresponding features in different viewpoints.
- analyse visual motion to recover scene structure and viewer motion, and understand how this information can be used in navigation;
- understand how simple object recognition systems can be designed so that they are independent of lighting and camera viewpoint.
- appreciate the commerical and industrial potential of computer vision but understand its limitations.
Content
- Introduction (1L)
Computer vision: what is it, why study it and how ? The eye and the camera, vision as an information processing task. Geometrical and statistical frameworks for vision. 3D interpretation of 2D images. Applications.
- Image structure (4L)
Image intensities and structure: edges, corners and blobs. Edge detection, the aperture problem and corner detection. Image pyramids, blob detection with band-pass filtering. The SIFT feature descriptor for matching. Characterising textures.
- Projection (4L)
Orthographic projection. Planar perspective projection. Vanishing points and lines. Projection matrix, homogeneous coordinates. Camera calibration, recovery of world position. Weak perspective and the affine camera. Projective invariants.
- Stereo vision and Structure from Motion (2L)
Epipolar geometry and the essential matrix. Recovery of depth by triangulation. Uncalibrated cameras and the fundamental matrix. The correspondence problem. Structure from motion. 3D shape examples from multiple view stereo.
- Deep Learning for Computer Vision (5L)
Basic architectures for deep learning in computer vision. Object detection, classification and semantic segmentation. Object recognition, feature embedding and metric learning. Transformer architectures and self-supervised learning.
- Example classes
Discussion of examples papers and past examination papers will be integrated with lectures.
Booklists
Please refer to the Booklist for Part IIB Courses for references to this module, this can be found on the associated Moodle course.
Examination Guidelines
Please refer to Form & conduct of the examinations.
UK-SPEC
This syllabus contributes to the following areas of the UK-SPEC standard:
Toggle display of UK-SPEC areas.
GT1
Develop transferable skills that will be of value in a wide range of situations. These are exemplified by the Qualifications and Curriculum Authority Higher Level Key Skills and include problem solving, communication, and working with others, as well as the effective use of general IT facilities and information retrieval skills. They also include planning self-learning and improving performance, as the foundation for lifelong learning/CPD.
IA1
Apply appropriate quantitative science and engineering tools to the analysis of problems.
IA2
Demonstrate creative and innovative ability in the synthesis of solutions and in formulating designs.
KU1
Demonstrate knowledge and understanding of essential facts, concepts, theories and principles of their engineering discipline, and its underpinning science and mathematics.
KU2
Have an appreciation of the wider multidisciplinary engineering context and its underlying principles.
D1
Wide knowledge and comprehensive understanding of design processes and methodologies and the ability to apply and adapt them in unfamiliar situations.
D4
Ability to generate an innovative design for products, systems, components or processes to fulfil new needs.
E1
Ability to use fundamental knowledge to investigate new and emerging technologies.
E2
Ability to extract data pertinent to an unfamiliar problem, and apply its solution using computer based engineering tools when appropriate.
E3
Ability to apply mathematical and computer based models for solving problems in engineering, and the ability to assess the limitations of particular cases.
P1
A thorough understanding of current practice and its limitations and some appreciation of likely new developments.
P3
Understanding of contexts in which engineering knowledge can be applied (e.g. operations and management, technology, development, etc).
US1
A comprehensive understanding of the scientific principles of own specialisation and related disciplines.
US2
A comprehensive knowledge and understanding of mathematical and computer models relevant to the engineering discipline, and an appreciation of their limitations.
US3
An understanding of concepts from a range of areas including some outside engineering, and the ability to apply them effectively in engineering projects.
US4
An awareness of developing technologies related to own specialisation.
Last modified: 28/09/2023 15:45
Engineering Tripos Part IIB, 4F10: Deep Learning & Structured Data, 2023-24
Module leader
Lecturer
Prof M Gales and Dr Miguel Hernandez-Lobato
Timing and Structure
Michaelmas term. 14 lectures + 2 examples classes. Assessment: 100% exam
Prerequisites
Part IIA Modules 3F1, 3F3 and 3F8 advisable
Aims
The aims of the course are to:
- This module aims to teach the basic concepts of deep learning and forms of structure that can be used for generative and discriminative models. In addition, the use of models for classifying structured data, such as speech and language, will be discussed
Objectives
As specific objectives, by the end of the course students should be able to:
- Understand the basic principles of pattern classification and deep learning;
- Understand generative and discriminative models for structured data;
- Understand the application of deep-learning to structured data;
- Be able to apply pattern processing techniques to practical applications.
Content
Introduction (1L)
Links with 3F8 and 4F13. General machine learning, examples of structured data, DNA, vision, speech and language processing.
Decision Boundaries and Probability of Error (1L)
Definition of a decision boundary and forms that result from Gaussian class-conditional probability density functions. Calculation of probability of Error.
Graphical Models and Conditional Indpendence (1L)
Graphical models and Bayesian networks. Simple inference examples.
Latent Variable and Sequence Models (3L)
Gaussian mixture models and factor analysis; hidden Markov models and expectation maximisation.
Deep Learning (2L)
Generative and discriminative deep models. Forms of network and activation functions. Convolutional neural networks, mixture-density neural networks. Optimisation approaches (first/second order methods, adaptive learning rates) and initialisation.
Deep Learning for Sequences (2L)
Recurrent neural networks, and long-short-term memory models. Variants of RNN including bidirectional RNNs. Use in generative and discriminative models.
Ensemble Methods (1L)
Ensemble methods: random forests, bagging, boosting and model combination.
Support Vector Machines (2L)
Maximum margin classifiers, handling non-separable data, training SVMs, non-linear SVMs, kernel functions. Multi-class SVMs.
Kernels over Structured Data (1L)
String kernels, graph kernels and Fisher kernels.
Booklists
Please refer to the Booklist for Part IIB Courses for references to this module, this can be found on the associated Moodle course.
Examination Guidelines
Please refer to Form & conduct of the examinations.
UK-SPEC
This syllabus contributes to the following areas of the UK-SPEC standard:
Toggle display of UK-SPEC areas.
GT1
Develop transferable skills that will be of value in a wide range of situations. These are exemplified by the Qualifications and Curriculum Authority Higher Level Key Skills and include problem solving, communication, and working with others, as well as the effective use of general IT facilities and information retrieval skills. They also include planning self-learning and improving performance, as the foundation for lifelong learning/CPD.
IA1
Apply appropriate quantitative science and engineering tools to the analysis of problems.
IA2
Demonstrate creative and innovative ability in the synthesis of solutions and in formulating designs.
KU1
Demonstrate knowledge and understanding of essential facts, concepts, theories and principles of their engineering discipline, and its underpinning science and mathematics.
KU2
Have an appreciation of the wider multidisciplinary engineering context and its underlying principles.
E1
Ability to use fundamental knowledge to investigate new and emerging technologies.
E2
Ability to extract data pertinent to an unfamiliar problem, and apply its solution using computer based engineering tools when appropriate.
E3
Ability to apply mathematical and computer based models for solving problems in engineering, and the ability to assess the limitations of particular cases.
P1
A thorough understanding of current practice and its limitations and some appreciation of likely new developments.
P3
Understanding of contexts in which engineering knowledge can be applied (e.g. operations and management, technology, development, etc).
P8
Ability to apply engineering techniques taking account of a range of commercial and industrial constraints.
US1
A comprehensive understanding of the scientific principles of own specialisation and related disciplines.
US2
A comprehensive knowledge and understanding of mathematical and computer models relevant to the engineering discipline, and an appreciation of their limitations.
Last modified: 30/05/2023 15:31
Engineering Tripos Part IIB, 4F10: Deep Learning & Structured Data, 2020-21
Module leader
Lecturer
Prof M Gales & Dr J M Hernandez-Lobato
Timing and Structure
Michaelmas term. 14 lectures + 2 examples classes. Assessment: 100% exam
Prerequisites
Part IIA Modules 3F1, 3F3 and 3F8 advisable
Aims
The aims of the course are to:
- This module aims to teach the basic concepts of deep learning and forms of structure that can be used for generative and discriminative models. In addition, the use of models for classifying structured data, such as speech and language, will be discussed
Objectives
As specific objectives, by the end of the course students should be able to:
- Understand the basic principles of pattern classification and deep learning;
- Understand generative and discriminative models for structured data;
- Understand the application of deep-learning to structured data;
- Be able to apply pattern processing techniques to practical applications.
Content
Introduction (1L)
Links with 3F8 and 4F13. General machine learning, examples of structured data, DNA, vision, speech and language processing.
Decision Boundaries and Probability of Error (1L)
Definition of a decision boundary and forms that result from Gaussian class-conditional probability density functions. Calculation of probability of Error.
Graphical Models and Conditional Indpendence (1L)
Graphical models and Bayesian networks. Simple inference examples.
Latent Variable and Sequence Models (3L)
Gaussian mixture models and factor analysis; hidden Markov models and expectation maximisation.
Deep Learning (2L)
Generative and discriminative deep models. Forms of network and activation functions. Convolutional neural networks, mixture-density neural networks. Optimisation approaches (first/second order methods, adaptive learning rates) and initialisation.
Deep Learning for Sequences (2L)
Recurrent neural networks, and long-short-term memory models. Variants of RNN including bidirectional RNNs. Use in generative and discriminative models.
Ensemble Methods (1L)
Ensemble methods: random forests, bagging, boosting and model combination.
Support Vector Machines (2L)
Maximum margin classifiers, handling non-separable data, training SVMs, non-linear SVMs, kernel functions. Multi-class SVMs.
Kernels over Structured Data (1L)
String kernels, graph kernels and Fisher kernels.
Booklists
Please refer to the Booklist for Part IIB Courses for references to this module, this can be found on the associated Moodle course.
Examination Guidelines
Please refer to Form & conduct of the examinations.
UK-SPEC
This syllabus contributes to the following areas of the UK-SPEC standard:
Toggle display of UK-SPEC areas.
GT1
Develop transferable skills that will be of value in a wide range of situations. These are exemplified by the Qualifications and Curriculum Authority Higher Level Key Skills and include problem solving, communication, and working with others, as well as the effective use of general IT facilities and information retrieval skills. They also include planning self-learning and improving performance, as the foundation for lifelong learning/CPD.
IA1
Apply appropriate quantitative science and engineering tools to the analysis of problems.
IA2
Demonstrate creative and innovative ability in the synthesis of solutions and in formulating designs.
KU1
Demonstrate knowledge and understanding of essential facts, concepts, theories and principles of their engineering discipline, and its underpinning science and mathematics.
KU2
Have an appreciation of the wider multidisciplinary engineering context and its underlying principles.
E1
Ability to use fundamental knowledge to investigate new and emerging technologies.
E2
Ability to extract data pertinent to an unfamiliar problem, and apply its solution using computer based engineering tools when appropriate.
E3
Ability to apply mathematical and computer based models for solving problems in engineering, and the ability to assess the limitations of particular cases.
P1
A thorough understanding of current practice and its limitations and some appreciation of likely new developments.
P3
Understanding of contexts in which engineering knowledge can be applied (e.g. operations and management, technology, development, etc).
P8
Ability to apply engineering techniques taking account of a range of commercial and industrial constraints.
US1
A comprehensive understanding of the scientific principles of own specialisation and related disciplines.
US2
A comprehensive knowledge and understanding of mathematical and computer models relevant to the engineering discipline, and an appreciation of their limitations.
Last modified: 01/09/2020 10:38
Engineering Tripos Part IIB, 4F10: Deep Learning & Structured Data, 2024-25
Leader
Lecturer
Prof M Gales, Dr J M Hernandez-Lobato
Timing and Structure
Michaelmas term. 14 lectures + 2 examples classes. Assessment: 100% exam
Prerequisites
Part IIA Modules 3F3 and 3F8 advisable, 3F7 3F4 useful but not required.
Aims
The aims of the course are to:
- This module aims to teach the basic concepts of deep learning and forms of structure that can be used for generative and discriminative models. In addition the use of models for classifying structured data, such as speech and language, will be discussed
Objectives
As specific objectives, by the end of the course students should be able to:
- Understand the basic principles of pattern classification and deep learning;
- Understand generative and discriminative models for structured data;
- Understand the application of deep-learning to structured data;
- Be able to apply pattern processing techniques to practical applications.
Content
Introduction (1L)
Links with 3F8 and 4F13. General machine learning, examples of structured data, DNA, vision, speech and language processing.
Graphical Models and Conditional Indpendence (1L)
Graphical models and Bayesian networks. Simple inference examples.
Generative and discriminative sequence models (2L)
Hidden Markov models and expectation maximisatiion (EM) - use for training Gaussian mixture models (GMMs) and Factor Analysis. Representation of these models as dynamic Bayesian networks. Conditional Random Fields (CRFs) as an example of a discriminative sequence model.
Deep Learning (3L)
Generative and discriminative deep models. Forms of network and activation functions. Convolutional neural networks, mixture-density neural networks. Optimisation approaches (first/second order methods, adaptive learning rates) and initialisation.
Deep Learning for Sequences (1L)
Recurrent neural networks, and long-short-term memory models. Variants of RNN including bidirectional RNNs. Use in generative and discriminative models.
Alternate Deep Network Architectures (1L)
Variational Auto Encoders (VAE) and variational estimation (possibly other examples: generative adversarial networks, Siamese networks).
Support Vector Machines (2L)
Maximum margin classifiers, handling non-separable data, training SVMs, non-linear SVMs, kernel functions. Links with other kernel methods Gaus- sian Processes, Relevance Vector Machines. Multi-class SVMs and structured SVMs.
Kernels over Structured Data (1L)
Tree kernels, graph kernels, Fisher kernels. Relationship to RNNs.
Traditional and Bayesian Non-Parametric Techniques(2L)
Classification and regression trees, parzen windows, K-nearest neighbours, nearest neighbour rule. Ensemble methods: random forests, bagging, boosting and model combination.
Booklists
Please see the Booklist for Group F Courses for references for this module.
Examination Guidelines
Please refer to Form & conduct of the examinations.
UK-SPEC
This syllabus contributes to the following areas of the UK-SPEC standard:
Toggle display of UK-SPEC areas.
GT1
Develop transferable skills that will be of value in a wide range of situations. These are exemplified by the Qualifications and Curriculum Authority Higher Level Key Skills and include problem solving, communication, and working with others, as well as the effective use of general IT facilities and information retrieval skills. They also include planning self-learning and improving performance, as the foundation for lifelong learning/CPD.
IA1
Apply appropriate quantitative science and engineering tools to the analysis of problems.
IA2
Demonstrate creative and innovative ability in the synthesis of solutions and in formulating designs.
KU1
Demonstrate knowledge and understanding of essential facts, concepts, theories and principles of their engineering discipline, and its underpinning science and mathematics.
KU2
Have an appreciation of the wider multidisciplinary engineering context and its underlying principles.
E1
Ability to use fundamental knowledge to investigate new and emerging technologies.
E2
Ability to extract data pertinent to an unfamiliar problem, and apply its solution using computer based engineering tools when appropriate.
E3
Ability to apply mathematical and computer based models for solving problems in engineering, and the ability to assess the limitations of particular cases.
P1
A thorough understanding of current practice and its limitations and some appreciation of likely new developments.
P3
Understanding of contexts in which engineering knowledge can be applied (e.g. operations and management, technology, development, etc).
P8
Ability to apply engineering techniques taking account of a range of commercial and industrial constraints.
US1
A comprehensive understanding of the scientific principles of own specialisation and related disciplines.
US2
A comprehensive knowledge and understanding of mathematical and computer models relevant to the engineering discipline, and an appreciation of their limitations.
Last modified: 20/02/2025 12:12
Engineering Tripos Part IIB, 4F10: Deep Learning & Structured Data, 2025-26
Module leader
Lecturer
Timing and Structure
Michaelmas term. 14 lectures + 2 examples classes. Assessment: 100% exam
Prerequisites
Part IIA Modules 3F1, 3F3 and 3F8 advisable
Aims
The aims of the course are to:
- This module aims to teach the basic concepts of deep learning and forms of structure that can be used for generative and discriminative models. In addition, the use of models for classifying structured data, such as speech and language, will be discussed
Objectives
As specific objectives, by the end of the course students should be able to:
- Understand the basic principles of pattern classification and deep learning;
- Understand generative and discriminative models for structured data;
- Understand the application of deep-learning to structured data;
- Be able to apply pattern processing techniques to practical applications.
Content
Introduction (1L)
Links with 3F8 and 4F13. General machine learning, examples of structured data, DNA, vision, speech and language processing.
Decision Boundaries and Probability of Error (1L)
Definition of a decision boundary and forms that result from Gaussian class-conditional probability density functions. Calculation of probability of Error.
Graphical Models and Conditional Indpendence (1L)
Graphical models and Bayesian networks. Simple inference examples.
Latent Variable and Sequence Models (2L)
Gaussian mixture models and factor analysis; hidden Markov models and expectation maximisation.
Deep Learning (3L)
Generative and discriminative deep models. Forms of network and activation functions. Convolutional neural networks, density neural networks. Optimisation approaches (first/second order methods, adaptive learning rates) and initialisation.
Deep Learning for Sequences (2L)
Recurrent neural networks and variants of RNN including bidirectional RNNs. Transformer architectures including encoder-only, encode-decoder and decoder only models. Aligning large-language models (LLMs) and Chain of Thought (CoT).
Ensemble Methods and Model Distillation (1L)
Deep ensembles, model combination and model distillation approaches.
Support Vector Machines (2L)
Maximum margin classifiers, handling non-separable data, training SVMs, non-linear SVMs, kernel functions. Multi-class SVMs.
Kernels over Structured Data (1L)
String kernels, graph kernels and Fisher kernels.
Booklists
Please refer to the Booklist for Part IIB Courses for references to this module, this can be found on the associated Moodle course.
Examination Guidelines
Please refer to Form & conduct of the examinations.
UK-SPEC
This syllabus contributes to the following areas of the UK-SPEC standard:
Toggle display of UK-SPEC areas.
GT1
Develop transferable skills that will be of value in a wide range of situations. These are exemplified by the Qualifications and Curriculum Authority Higher Level Key Skills and include problem solving, communication, and working with others, as well as the effective use of general IT facilities and information retrieval skills. They also include planning self-learning and improving performance, as the foundation for lifelong learning/CPD.
IA1
Apply appropriate quantitative science and engineering tools to the analysis of problems.
IA2
Demonstrate creative and innovative ability in the synthesis of solutions and in formulating designs.
KU1
Demonstrate knowledge and understanding of essential facts, concepts, theories and principles of their engineering discipline, and its underpinning science and mathematics.
KU2
Have an appreciation of the wider multidisciplinary engineering context and its underlying principles.
E1
Ability to use fundamental knowledge to investigate new and emerging technologies.
E2
Ability to extract data pertinent to an unfamiliar problem, and apply its solution using computer based engineering tools when appropriate.
E3
Ability to apply mathematical and computer based models for solving problems in engineering, and the ability to assess the limitations of particular cases.
P1
A thorough understanding of current practice and its limitations and some appreciation of likely new developments.
P3
Understanding of contexts in which engineering knowledge can be applied (e.g. operations and management, technology, development, etc).
P8
Ability to apply engineering techniques taking account of a range of commercial and industrial constraints.
US1
A comprehensive understanding of the scientific principles of own specialisation and related disciplines.
US2
A comprehensive knowledge and understanding of mathematical and computer models relevant to the engineering discipline, and an appreciation of their limitations.
Last modified: 05/06/2025 11:55
Pages
