PhD Studentship - Anomaly Detection Using Deep Learning

Durham University - Department of Computer Science

Applications are invited for a fully funded PhD student to work within Engineering and Computing Science at Durham University on the topic of developing deep learning based anomaly detection in collaboration with Cosmonio (www.cosmonio.com).

Recent Deep Neural Network research has led to a significant performance leap in pattern-recognition tasks such as computer vision (image understanding), text mining (language understanding) and voice recognition (audio understanding).

This project looks beyond the initial applications of such technology, largely aimed at the classification of images, words and sound to a set of expected semantic labels to the problem of anomaly detection. Asking the novel research question - what is different from normal here within this stream of data? - rather than specifically identifying the {pixel | text | word ...} pattern for {person | vehicle | dog …} etc in the conventional sense. This looks to address ongoing analogy detection challenges in medical data understanding (lead:  Cosmonio), robotics and artificial intelligence (data understanding for future autonomous systems), surveillance and security screening systems and future driver-less vehicles (understanding the unexpected in the on-road and off-road environment).

The project will take the form of an industrially supported studentship with the student primarily based at Durham University whilst ideally working for short industrial placement periods with Cosmonio throughout the PhD. This represents a very good opportunity for a candidate interested in an applied research career, comprising both academic and industrial placement elements within the 4 year funded study programme.

COSMONiO, an SME a with bases in the UK and the Netherlands, designs cutting-edge computer-vision and machine-learning systems that automate the process of extracting visual information from images and other data sources (www.cosmonio.com). An overview of related research work at Durham team is available from http://www.durham.ac.uk/toby.breckon/demos/ (spanning automotive sensing, surveillance and security screening work).

Entry Requirements: Applicants should hold at least a 2:1 honours degree or equivalent in Computer Science, Engineering, Physics or a related technical discipline (Masters degree a plus) with a strong programming ability in a high level language and a highly competent mathematical background. Prior experience in computer vision, image processing and/or machine learning is a plus although not essential.

Eligiability: This studentship is only available to UK/EU nationals who have been resident in the UK for the last 3 years (see: http://www.epsrc.ac.uk/skills/students/help/eligibility/). Studentship awards are available to cover both tuition fees and a stipend in the form of a tax-free subsistence bursary for both (in line with EPSRC recommendations, http://www.epsrc.ac.uk/skills/students/help/minimumpay/). Non-EU applicants, or EU-applicants not residing in the UK, are not eligible for this award unless they can demonstrate a relevant connection to the UK.

How to apply: Applicants can make initial informal enquiries with Dr. Toby Breckon, toby.breckon@durham.ac.uk

If you meet the eligibility criteria please make an application via the university applications page at: https://www.dur.ac.uk/postgraduate/apply/ (specifying project title: Anomaly Detection Using Deep Learning, supervisor: Dr. Toby Breckon, Engineering and Computing Science; applications cannot be accepted by email). Applications are for immediate start in Autumn 2017.

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