This module is the project phase of the MRes degree in Visual Computing.
This module provides a broad introduction to artificial intelligence, machine learning, pattern recognition, and their applications to big data problems. The students will gain understanding and knowledge of the theoretical foundations of learning, learn effective machine learning techniques, and acquire practical know-how in applying some of those theories and techniques to real world problems. Topics include big data concept, data mining, learning theories, supervised and unsupervised learning, and reinforcement learning.
In this module students will be presented with an overview of the research area of Visual Computing. They are introduced into the topic, the background and the aims of their project. They write a detailed specification which will be the basis of their research project. Guidance as to appropriate research methodologies is provided.
This module will introduce students to some fundamental research methodologies and good practice in research. They will undertake background research including a literature review and specify the aims of their MSc project.
This module will discuss in-depth some of the most widely used and state-of-the-art artificical intelligence and machine learning techniques and their applications to big data problems. The students will gain both theoretical understanding of learning and practical know-how in applying those theories to real world problems. Topics include big data concept, data mining, learning theories, supervised and unsupervised learning, and reinforcement learning.
This module introduces students to the important and modern topics and concepts of computer vision and deep learning, including image processing, feature extraction, camera calibration, stereo vision, motion and tracking, recognition, deep neural network and its application to vision problems. It teaches techniques that are used to understand and interpret the contents of images and videos and dissects state-of-the-art vision systems, such as Microsoft Kinect. Practical examples in Matlab are provided throughout the lectures.
|Start Date||End Date||Position Held||Location|
|March 2019||Present||Professor||Department of Computer Science, Swansea University|
|April 2013||February 2019||Associate Professor||Department of Computer Science, Swansea University|
|October 2012||March 2013||Senior Lecturer||Department of Computer Science, Swansea University|
|September 2007||September 2012||Lecturer (RCUK Academic Fellow)||Department of Computer Science, Swansea University|
|August 2007||September 2007||Research Associate||Department of Computer Science, Bristol University|
|February 2006||July 2007||Research Assistant||Department of Computer Science, Bristol University|
|February 2011||November 2005||Research Assistant and PhD Student||Department of Computer Science, Bristol University|
led by Prof. John (Bangor University), Funded by NISCHR, £325K to Swansea (£1.5M in total)
led by Dr. van Lool (Swansea University), Funded by NISCHR, £58K
, Funded by WORD, £144K
led by Prof. Zwiggelaar (Aber University), Funded by NISCHR, £95K
led by Prof. Mirmehdi (Bristol University), Funded by The Leverhulme Trust, £65K
Co-PI, funded byI nnovateUK, £319,514.40
PI, funded by InnovateUK, £172,139.08
PI, SÊR CYMRU Cofund, £63,082.35
Co-investigator, led by Prof. Mark Jones (Swansea), funded by EPSRC (EP/N028139/1 and EP/N027825/1) £1.6M
, Funded by WAG, £5M