PhD Opportunity Title: Implementation of machine learning at the edge
Advert Text: The demand for AI applications at the edge is rising mainly due to the rapid improvements of deep learning methodologies and Internet of Things (IoT) devices. Transfer of cloud-based tasks to the edge alleviates issues such as high latency and privacy. However computationally intensive AI tasks are not suitable for most edge devices with limited memory, processing and power capabilities. High popularity of AI applications at the edge demands adaptations in machine learning strategies to match better with resource-limited/low-power edge devices, and also in optimising hardware design (including CPUs, FPGAs, etc.) to have efficient memory, compute, and specifically power consumption features suitable for AI tasks.
The focus of this PhD project is on developing novel compute-intensive neural network models and also hardware design for training and deploying these models at the edge. Exploring new network models and hardware designs are required so that the applications are adapted and tailored for hardware, to efficiently exploit the limited edge device resources. Successful outcome would have positive impact on a wide range of AI application implementations on resource-constraint devices, including IoT and mobile devices.
Is the project University funded or self-funded?: University funded
Funding eligibility: Competition funded project (students worldwide)
Who is eligible to apply?: Both UK and International
Full-time/part-time availability: Full-time (3 years)
Closing Date: 18th September 2022
Advert Reference: P2SAM22-01
Apply Link:https://www.lboro.ac.uk/study/postgraduate/apply/research-applications/