Etudes Non Stop Study Non Stop
Related Articles
In the past decade, neural-networks have gained a lot of popularity and are being widely used in object recognition, data analysis and classification tasks of smart-car,-city,-health applications. Traditionally, neural-networks are designed for optimal prediction capabilities through large-scale and dense connectivity without considerations for practical implementations, and thus they end-up being very computationally intensive and power hungry. However, as Neural-Networks are increasingly being used in various devices in Edge and Cloud environments, where power consumption is a primary concern, the attention of industry and users turns into energy-efficient Neural-Networks. To this end, the primary aim of this project is the acceleration of Neural-Networks at the right energy and accuracy based on dynamic task-scheduling and accuracy-adaptation on heterogeneous devices at the Edge and Cloud. This will be achieved by designing new low-cost hardware mechanisms and combining them with intelligent runtime support that ensure each task is dynamically precision tailored based on the informational value of the processed data as well as the operating conditions and available resources on shared multi-tenant environments at the Edge and Cloud. The developed cross-layer mechanisms will allow to exploit the inherent resilient properties of NNs and dynamically tune the data-dependent precision controls to opportunistically scale resource provisioning for step-changing energy-efficiency and resilience. As the main case study, we will use Object Recognition in Video Streams, which is extremely important in emerging secure surveillance and smart-city applications including self-driving cars. The Neural-Network and mechanisms will be developed on reconfigurable hardware, i.e. Field Programmable Gate Arrays (FPGAs), which offers the required flexibility for architectural optimizations that is not available in existing processors used by most of the current works. Such devices have already started being used in Cloud datacentres like Amazon’s and are excellent candidates for emerging Edge deployments, which we plan to further enable by the developed mechanisms.
The project brings together experts on hardware design and computer vision from ECIT Global Research Institute and on FPGA prototyping of machine learning from XILINX Research.
Employment & Salary:
The researcher will be employed as staff, with the title of Early-Career-Researcher, of Queen’s University, under an enhanced renumeration package of £28925/year! The researcher will have access to a specialized academic and industrial training program and join a team of 20 other ECRs on smart networked societies.
Eligibility Criteria:
Applicants must be in the first four years of their research careers and must not have been awarded a doctoral degree. Researchers shall not have resided or carried out their main activity in United-Kingdom for more than 12 months in the past 3 years.
Desirable Criteria:
- Evidence of exceptional academic achievements
- Evidence of outstanding skills relevant to the position, i.e.
FPGA design flow, c/opencl/python, vhdl/verilog, porting of machine learning/signal processing algorithms on FPGAs, accelerators, arithmetic units. - Have already a publications or eager to publish at top-tier conferences/journals.
Interested applicants that meet the eligibility criteria must apply to the link with a CV and cover letter explaining how they meet the desirable criteria.
Applicants are also strongly encouraged to contact g.karakonstantis@qub.ac.uk with a CV and a short description of their relevant skills to indicate their interest.
