Creative intelligence: Unsupervised representation learning for computational creativity
Start date1 October 2019
Funding will provide an annual tax-free stipend of approximately £20,000 and coverage of the home/EU tuition fees for 3.5 years. Based at Surrey. Opportunity for internship and travel to Adobe in the Bay Area.
Funding sourceUniversity of Surrey CDT for Audio-Visual Machine Perception (AVMP) co-funded by Adobe Research
By joining CVSSP you will be accessing the newly formed Centre for Doctoral Training in Audio-Visual Machine Perception (CDT-AVMP) at the University of Surrey.
The CDT-AVMP offers an enhanced 3.5 year doctoral training programme to address industry demand for individuals with cross-disciplinary scientific expertise in AI and Machine Perception, working in teams with integrated professional skills in software, project management, innovation and understanding of ethics and regulation of AI and data science research.
The project will investigate unsupervised and self-supervised methods to learn computational models of creativity from large volumes of digital creative work. The PhD will focus upon developing new deep learning techniques to understand and synthesize many forms of creative output, including digital artwork, user experiences (e.g. UI layouts). It will explore how these models could be incorporated into AI-enabled tools, and designers can co-create with those tools in a closed loop to enhance their creative process.
The project will explore learning disentangled representations of content structure and style via self-supervised networks, and generative models for in-flow design recommendations to help guide novice designers or apply stylistic transformations to designs.
The PhD is co-supervised between the Centre for Vision Speech and Signal Processing (CVSSP) and Adobe Research’s Creative Intelligence Lab (CIL) based in San Jose, California. Adobe will be closely involved in the supervision of this project and opportunities exist for internship and travel to Adobe HQ in Silicon Valley during the project.
Related linksCentre for Vision, Speech and Signal Processing
- A first class or 2:1 honours degree (or equivalent overseas qualification) in an appropriate discipline (e.g. engineering, computer science, signal processing, applied mathematics, and physics)
- You should be able to demonstrate excellent mathematical, analytic, programming skills
- IELTS academic: 6.5 or above (or equivalent) with no sub-test of less than 6.
- Previous experience in computer vision, machine/deep learning, or augmented reality would be advantageous.
This directly funded project is only available to European and UK students.
How to apply
You can apply for this studentship by applying for the Vision, Speech and Signal Processing PhD. Please clearly state the studentship title in your application.
Vision, Speech and Signal Processing PhD
About the Centre for Vision Speech and Signal Processing (CVSSP)
Our Centre is ranked number one for Computer Vision in the UK and it is one of the largest in Europe with over 150 researchers and a grant portfolio in excess of £23million. CVSSP brings together a unique combination of cutting-edge sound and vision expertise, with an outstanding track-record of innovative research leading to technology transfer and exploitation in biometrics, creative industries (film, TV, games, VR, AR), mobile communication, healthcare, robotics, autonomous vehicles and consumer electronics.
Postgraduate research with CVSSP
CVSSP promotes an exciting, supportive and inclusive research environment. Secondments with industry and international groups are encouraged during the PhD to broaden experience and to ensure research is kept relevant to real-world problems. Our PhD researchers contribute to advancing the state-of-the art through publication and by participating in leading international forums.
The Postgraduate Research Experience Survey (PRES) 2018 ranked the University of Surrey 7th in the UK out of 63 and 4th for retention and completion.