Fully Funded PhD Studentship in Automated Behaviour Generation for Ultra-Adaptive Systems

Lancaster University

In Brief:

  • Topic: Self-writing, self-assembling and adaptive systems
  • Closing Date: September 15th, for October 1st start
  • Eligibility: UK Students, EU Students
  • Funding: Annual tax-free stipend of £14,533 (which will increment yearly)
  • Hours: Full Time

Details

This project aims to develop novel theory and implementation to enable entire distributed software systems to autonomously self-assemble from a large set of small behaviours, with no human input in this process, to satisfy a given goal. This will help to address the growing problem of software complexity, in which human developers are required to have extremely high levels of input into the design, implementation, maintenance and deployment of software. Once a functional system (or system of systems) has been assembled using our approach, these systems will then continually discover their own capabilities by learning about the different ways in which they can assemble themselves and how those assemblies affect their performance under different conditions. All of this happens while a target software system is live, running in its normal production environment, so that everything is learned based on the reality to which the system is actually subjected.

This fully-funded PhD opportunity (fees plus living costs) will specifically explore the automated generation of new behaviours that are judged to be useful to the running system. The PhD will explore the use of techniques such as genetic programming, neural networks, and trajectory computing, to capture runtime requirements regarding the kinds of environment to which a software system is being subjected, and to feed this information into a component generation system which automatically writes new behaviours that are better suited to those observed environment conditions. These generated components will then be seamlessly integrated into the live system to assess their effectiveness. You will explore the most efficient ways to generate the most highly suitable code for the runtime conditions being experienced, to have computers learn about the nature of algorithms and computation so that further code generation builds on past experience, and to keep human developers in the loop about automatically generated systems.

Requirements

Candidates should have a 1st class degree (or equivalent) in computer science or a closely related discipline with an interest in distributed systems, machine learning, and code generation. Good programming skills are essential. Experience in system orchestration, component-based development, and applied machine learning are useful but not required.

Application details

Please apply online via the University Postgraduate Admissions Portal at http://www.lancaster.ac.uk/study/postgraduate/how-to-apply-for-postgraduate-study/ with:

  • A CV (2 pages maximum)
  • Cover letter
  • University grade transcripts

Note that no proposal is required as part of the application, though evidence of research vision and relevant background knowledge on the state of the art in this area is strongly encouraged. You should clearly state on your application that you are applying for a funded PhD opportunity on “Automated Behaviour Generation for Ultra-Adaptive Systems”.

Contact Us

We very much welcome informal queries about this opportunity, which should be directed to Dr. Barry Porter (b.f.porter@lancaster.ac.uk).

Share this PhD
     
  Share by Email   Print this job   More sharing options
We value your feedback on the quality of our adverts. If you have a comment to make about the overall quality of this advert, or its categorisation then please send us your feedback
Advert information

Type / Role:

PhD

Location(s):

Northern England