PhD in Optics or AI Computer Vision starting in May 2022
The School of Engineering and Informatics are looking to fund a PhD studentship in the Industrial Informatics and Signal Processing group (IISP). The IISP group actively researches in the areas of optics and computer vision and is looking for a research student in one of the following areas of research.
- Optical deep learning systems. Deep learning has provided a massive benefit to science and industry in the last few years. However, the electrical power requirements for implementing the system on an industrial scale is huge. One alternative is to implement some of the processing optically. Using spatial light modulators and the Fourier transforming properties of lenses, convolutions can be calculated at the speed of light using milliWatts of energy. The optical system has more noise than an electrical equivalent so some clever designs are needed to overcome this. This project will investigate the designs, model and potentially implement the system. The student will need to model and train the network using PyTorch.
- Optical Comms using LiFi. Using holographic beam control a laser can be used to transmit information to any point within a room. This allows for high speed, secure, point to point communications, replacing congested wifi spectrum. The project will look at the design of non-diffracting beams that can be used to increase the range of transmission.
- Medical Cancer Diagnostics. By using deep learning, computers can learn to recognise the tell-tale signs of cancers in various medical imaging modalities such as MRI. This project will use datasets provided by medics to develop novel AI architects to detect lung and breast cancers. The aim is to locate possible cancers as early as possible since early intervention will greatly enhance the survivability of the cancer. The project will use CUDA accelerated deep learning in Python so the applicant should have a background in computing and/or AI.
- The tracking of people and objects across multiple cameras is a difficult problem. In addition, there are often only a few pixels viewing the object. This low resolution is difficult for deep learning networks. This project will look at trying to solve these problems. There are many applications, from the tracking of people in public spaces such as airports and railway stations, detecting the difference between a drone and a bird, to identifying birds, bats and wildlife for conservation efforts.
A physics, engineering or computer sciences degree is expected, but we would consider others on a case-by-case basis. For more details, please contact Dr Phil Birch: [Email Address Removed]
Apply online for a full time PhD in [Informatics/Engineering] using our step-by-step guide (http://www.sussex.ac.uk/study/phd/apply). Here you will also find details of our entry requirements.
Please clearly state on your application form that you are applying for the PhD in Optics or AI Computer Vision Scholarship with Dr Phil Birch, Prof Chris Chatwin, Dr Rupert Young. The start date for this PhD is May 2022.
Application deadline: 28/02/2022
Interview date: March 2022
Notification date: March 2022
Start date: May 2022