|Funding for:||UK Students, EU Students|
|Placed On:||25th March 2019|
|Closes:||20th May 2019|
Funding amount: £15,000 maintenance grant per annum
Lead Supervisor name: Dr Feng Tian
Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. The deep learning models, especially convolutional neural networks, have achieved impressive successes in fields such as object recognition and complex games. This project aims to establish a novel neural network model simulating human brain's visual cortex, which is capable of capable of recognizing distorted patterns as well as tolerating positional shift. The model can learn from the stimulus patterns with shift invariance ability and can be generalized to recognize any unseen deformed version of these patterns. With the foreseen advancements and advantages over existing methods, the proposed approach may generate more optimal models from natural or induced observations. The visual/image recognition tasks handled by the models may not be only limited to the supervised learning (trained with labelled data), but also include those unsupervised cases. Obviously, the power of recognition and classification of deep learning models could be significantly strengthened.
What does the funded studentship include?
Funded candidates will receive a maintenance grant of £15,000 per annum (unless otherwise specified), to cover their living expenses and have their fees waived for 48 months. In addition, research costs, including field work and conference attendance, will be met.
Funded Studentships are open to both UK/EU and International students unless otherwise specified.
Candidates for funded PhD studentship must demonstrate outstanding qualities and be motivated to complete a PhD in 4 years.
Studentship candidates must demonstrate outstanding academic potential with a 1st class honours degree and/or a Master’s degree with distinction. An IELTS (Academic) score of 6.5 minimum (with a minimum 6 in each component) is essential for candidates for whom English is not their first language.
In addition to satisfying basic entry criteria, BU will look closely at the qualities, skills and background of each candidate and what they can bring to their chosen research project in order to ensure successful and timely completion.
Closing date: The first call for applications will close on 20 May 2019.
For further information on how to apply click the ‘Apply’ button below or email firstname.lastname@example.org
Type / Role: