Job Description

Directorate: School of Engineering & Physical Sciences

Grade: Grade 7 (£36,924-£46,485)

Contract Type: Full Time (1FTE), Fixed Term (18 Months)

Rewards and Benefits: 33 days annual leave, plus 9 buildings closed days (and Christmas Eve when it falls on a weekday) for all full time staff. Use our total rewards calculator: https://www.hw.ac.uk/about/work/total-rewards-calculator.htm to see the value of benefits provided by Heriot-Watt University

Detailed description

The PDRA will work as part of the Prosperity Partnership between Heriot-Watt University, the University of Edinburgh and Leonardo UK. This project aims to address the current limitations of traditional frame-based sensors and associated processing pipelines with a new family of algorithmic architectures that mimic more closely the behaviours of biological brains.

Spiking neural networks (SNNs) can offer increased processing speed and reduced power consumption, especially when implemented on dedicated hardware (neuromorphic chips or FPGAs). Standard SNNs are typically fed with spiking data (e.g., streams of binary values), and the output of each layer remains spiking. They are particularly well suited for several new sensors, such as event-cameras, or single-photon detectors (used for single-photon Lidar), that natively produce event-like data that is compatible with spiking networks. Similarly, detection events from RF (radar and electronic surveillance) sensors can also be seen as temporal events. While data from current sensors can be manually converted into events for fast processing, it is also possible to develop hybrid structures where some layers (such as the input and/or output layer) are traditional (continuous) layers.

SNNs appear promising at the conceptual level but they currently suffer from limitations preventing the broad deployment. First, efficient and scalable training procedure are still needed, irrespective of whether the training is done off-line on a traditional GPU-based architecture, on neuromorphic hardware. Second, deployment of SNNs on actual neuromorphic hardware can come with additional structural constraints on the SNNs, such that quantization of the network weights which induces additional constraints on the training strategies.

In this project, we will investigate Bayesian methods to train deterministic SNNs (with deterministic activation functions) or probabilistic SNNs. Bayesian deep learning methods have been shown to accelerate and improve the training procedure of SNNs by defining new cost functions that are differentiable and easier to optimize. They can also handle quantized weights, e.g., using the reparameterization trick. Still, while methodological tools (first principles) exist, their application to solve real world problems still need to be demonstrated. This is what we intend to achieve in this project.

Research Environment

The project is in collaboration with two partners: (i) IDCOM at the University of Edinburgh, which develops theory, algorithms and hardware for the next generation of signal processing, imaging and communication systems and (ii) Leonardo UK, providing application expertise and end-user feedback. The applicant will be expected to work directly with Dr. Yoann Altmann, Prof. Steve McLaughlin from the Institute of Sensors and Signals (ISS) at Heriot-Watt University and Prof. Mike Davies at the University of Edinburgh, Leonardo staff, PhD students and the other PDRAs at the collaborating partner institutions.

The PDRA will report on project progress and outcomes to the Prosperity Partnership Management Group, as well as participating in Knowledge Transfer Meetings and Workshops with a broad range of Leonardo personnel.

Most of the project will be executed, in the at Heriot-Watt University in Edinburgh, with some joint work also executed at Leonardo UK, Edinburgh.

Key Duties and Responsibilities

• We are looking for a creative and highly motivated researcher willing to work as part of a team. Good communication skills and an appropriate publication record are essential.
• General tasks will involve scientific research; analysis and interpretation of data; daily oversight of the activities of postgraduate and undergraduate project students in the laboratory; communication with other investigators involved in this collaborative project; preparation of scientific papers; presentation of research at conferences whilst also supervising the activities of junior group members and PhD students.
• The successful candidate will be expected to contribute to experimental design and procedure as part in a collaborative decision-making process, while taking responsibility for implementing experiments, theoretical models and data analysis.
• Responsibilities will also include assistance in the day-to-day maintenance of the experimental facilities, liaising with external collaborators, assisting in the development of student research skills, and contributing to teaching (lab and tutorial demonstrations) in relevant taught courses within Engineering.
• The successful candidate is also expected to be involved in our outreach activities, with roles that can be tuned to the specific preferences of the candidate but will involve for example interviews, talks for the general public and preparation of experimental demonstrators for use in schools.

Is there room to grow? We encourage our researchers to find and follow their passion. We offer fantastic opportunities for learning, development and professional growth. This project will provide hands-on insight into, and potentially lead to, career opportunities at Leonardo. This is a chance of reinventing and developing your technical skillset during this exciting, challenging project. Learning on the job isn't just a benefit - it's a must.

Education, Qualifications and Experience

Essential Criteria

• Applicants should hold a PhD in a relevant area of Engineering, Mathematics, Physics or related subject (or a thesis submitted by the start date of the position).
• Ability to articulate research work, both in written technical reports / papers and by oral presentation.
• Must have proven academic ability and a demonstrable high level of technical competence in computational data science and the analysis / modelling of the results.
• Theoretical or experimental experience of in an area of direct relevance to the project.
• Ability to formulate and progress work on their own initiative with evidence of research ability: problem solving, flexibility.
• Must be able to work as part of a team at Heriot-Watt out with the specific project and more widely with the collaborators at other Universities.

Desirable Criteria

• Experience in leading the writing of scientific papers.
• Strong theoretical understanding of statistical machine learning methods relevant to the project: Bayesian learning, machine learning, spiking neural networks.
• Experience of programming (e.g. with Python) and data analysis.
• Evidence of ability, subject to opportunity, to guide other researchers, e.g. PhD students and undergraduate project students.
• Ability and willingness to learn new digital skills and capabilities appropriate to your role and how it evolves.
• Understand and adhere to information security practices particularly as it relates to personal or sensitive information.

About our Team

The School of Engineering & Physical Sciences has an international research reputation and close connection with the professional and industrial world of science, engineering and technology. Our research ranges from fundamental sciences through to engineering applications, all of which are supported by strong external funding. We have around 150 full-time academic staff who drive this research activity and are based in 5 research institutes: the Institute of Chemical Sciences, the Institute of Photonics & Quantum Sciences, the Institute of Mechanical, Process & Energy Engineering, the Institute of Sensors, Signals & Systems (ISSS) and the Institute of Biological Chemistry, BioPhysics & BioEngineering. REF2014 named Heriot-Watt in the top 25% of UK universities, with 82% of our research ranked as world-leading or internationally excellent. Heriot-Watt ranked 9th university in the UK and 1st in Scotland for research impact.

The School of Engineering & Physical Sciences has received the Bronze Award from the Athena SWAN Charter recognising excellence in championing employment of women in the fields of science and technology, engineering and mathematics.

In addition, we deliver teaching across 6 undergraduate and post-graduate programmes: Chemistry; Physics; Electrical, Electronic & Computer Engineering; Chemical Engineering; Mechanical Engineering and Brewing & Distilling. In the 2019 National Student Survey Heriot-Watt University was ranked 35th in the UK. 90% of our students were satisfied overall with their course in over half of the University's subject areas. At subject area level the School ranked in the top 10 UK universities for Physics and we were 3rd in Scotland for Chemistry and 2nd for Mechanical Engineering and 1st in Scotland for Chemical Engineering.

With 40 academic members of staff spanning 10 nationalities and 4 fields of expertise, ISSS aims to offer the full portfolio of expertise in the fields of signal and image processing, novel manufacturing technologies, microsystems, microwave engineering, mobile communications systems and autonomous systems. Of particular interest to ISSS is the design, modelling, simulation, processing of information from and system integration of sensors. The Signal and Image Processing Laboratory (SIPLab) at Heriot-Watt specializes in the design of advanced data science techniques with

applications ranging from robotics to imaging and communication, in a large variety of fields including defence, astronomy, art investigation, or medicine. Our research activities range from signal and image processing theory to application, and impact different areas of society. SIPLab is active in both traditional and emerging areas, and currently covers the following topics:

Signal and image processing theory

Statistical signal processing, non-stationary processes, Bayesian inference, signal models, sampling theory, sensing techniques, optimisation theory and algorithms, multi-modal data processing, high-performance computing, mathematical image analysis, geometric modelling, acoustic signal propagation, Monte Carlo simulation methods, decision theory, uncertainty quantification, machine learning.

Applications and areas of key innovation

Image analysis, computer graphics, autonomous and assisted driving, 3D scene analysis.

Leonardo is the UK's largest manufacturer of the sensors and electronic systems which sit under the skin of the world's most advanced aircraft, effectively acting as their brains, senses and nervous systems. Protecting pilots, alerting air crews to threats and providing unrivalled situational awareness, our world-class engineering and technology informs decision-making and helps ensure that those in harm's way come home safely.

Travel

The project consortium is based in Edinburgh and while the candidate is expected to be primarily based at HWU, monthly travels within Edinburgh (UoE, Leonardo) are expected.

Annual national conference (2-3 days within the UK) and at least 1 international conference (~ 1 week) as well as semi-regular travel between Heriot-Watt University, the University of Edinburgh and Leonardo is also expected.

About Heriot-Watt

Heriot-Watt University has established a reputation for world-class teaching and leading-edge, relevant research, which has made it one of the top UK universities for innovation, business and industry.

Nearly 30,000 students study with Heriot-Watt across business, engineering, design and the social, physical, biological and sports sciences. Our student body is roughly split evenly between the UK, our two campuses in Dubai and Malaysia, and online, with the latter being distributed across almost all the countries of the world. We also have many partnerships with other institutions world-wide who award Heriot-Watt degrees.

How to Apply

Please submit via the Heriot-Watt on-line recruitment system (1) Cover letter describing their interest and suitability for the post; (2) Full CV

Applications can be submitted until midnight on Thursday 12th December 2024.

For further information and an informal discussion, please contact Dr Yoann Altmann via email y.altmann@hw.ac.uk

At Heriot Watt we are passionate about our values and look to them to connect our people globally and to help us collaborate and celebrate our success through working together. Our research programmes can deliver real world impact which is achieved through the diversity of our international community and the recognition of creative talent that connects our global team.

Our flourishing community will give you the freedom to challenge and to bring your enterprising mind and to help our partners with solutions that can be applied now and in the future. Join us and Heriot Watt will provide you with a platform to thrive and work in a way that also helps you live your life in balance with well-being and inclusiveness at the heart of our global community.

Heriot-Watt University is committed to securing equality of opportunity in employment and to the creation of an environment in which individuals are selected, trained, promoted, appraised and otherwise treated on the sole basis of their relevant merits and abilities. Equality and diversity are all about maximising potential and creating a culture of inclusion for all.

Heriot-Watt University values diversity across our University community and welcomes applications from all sectors of society, particularly from underrepresented groups. For more information, please see our website https://www.hw.ac.uk/uk/services/equality-diversity.htm and also our award-winning work in Disability Inclusive Science Careers https://disc.hw.ac.uk/ .

We welcome and will consider flexible working patterns e.g. part-time working and job share options.

Use our total rewards calculator: https://www.hw.ac.uk/about/work/total-rewards-calculator.htm to see the value of benefits provided by Heriot-Watt University.