Fast implementation of Deep Neural Networks for IoT devices
Deep neural networks (DNNs) have found great success in many computer vision-related tasks. However, most of the existing DNNs require high computation and storage cost. In this project, the student will investigate how to implement DNN efficiently on low-powered IoT devices. The focus is on DNN model size reduction, fast implementation and efficient communication of DNN feature vectors under power and bandwidth constraints. The main focus is on vision-based tasks. But it could be used for other DNN related applications as well.
How to apply
If you are interested in applying for the above PhD topic please follow the steps below:
- Contact the supervisor by email or phone to discuss your interest and find out if you woold be suitable. Supervisor details can be found on this topic page. The supervisor will guide you in developing the topic-specific research proposal, which will form part of your application.
- Click on the 'Apply here' button on this page and you will be taken to the relevant PhD course page, where you can apply using an online application.
- Complete the online application indicating your selected supervisor and include the research proposal for the topic you have selected.
This is a self funded topic
Brunel offers a number of funding options to research students that help cover the cost of their tuition fees, contribute to living expenses or both. See more information here: https://www.brunel.ac.uk/research/Research-degrees/Research-degree-funding. The UK Government is also offering Doctoral Student Loans for eligible students, and there is some funding available through the Research Councils. Many of our international students benefit from funding provided by their governments or employers. Brunel alumni enjoy tuition fee discounts of 15%.
Meet the Supervisor(s)
Dr. Lu Gan received her B. Eng and M. Eng. degrees from South East University, China and the Ph.D degree from Nanyang Technological University, Singapore in 1998, 2000 and 2004 respectively. She is currently a senior lecturer (equivalent to associate professor) in Brunel University, London. Before she joined Brunel University in 2008, she has been on the faculties with The University of Newcastle (2004-2006), Australia and University of Liverpool, UK (2006-2007). From 2003 to 2004, she was a research associate in Centre for Signal Processing, Nanyang Technological University.
Dr. Gan’s research interests include fundamental signal processing theories and their applications in image/video coding and processing, non-destructive terahertz and ultrasound imaging, machine learning and wireless communications etc. Her research work has been funded by Australian research council, The Engineering and Physical Sciences Research Council (EPSRC) UK and TWI UK. She is a member of IEEE and a regular reviewer for many top journals including IEEE Transactions on Information theory, IEEE Transactions on Signal Processing, IEEE transactions on Communications and IEEE transactions on image processing etc. She has also been reviewing research grants in UK EPSRC and UK STFC and FWO in Belgium (equivalent to EPSRC in UK). She has been on the technical committee member for conferences including Globecom and ICC.
So far, she has more than 30 publications on journals with high impact factor and more than 60 conference publications. She has been working as Ph. D thesis/viva examiner for more than 20 candidates in UK and Australia. Her google scholar file can be found here.