Imperial College London Featured PhD Programmes
Sheffield Hallam University Featured PhD Programmes
Norwich Research Park Featured PhD Programmes
The University of Manchester Featured PhD Programmes
Cardiff University Featured PhD Programmes

PhD Position: Deep Reinforcement Learning for Computer Vision

Project Description


Nowadays, machine learning, deep neural networks in particular, quickly become a viable means for solving real-life computer vision problems such as object detection, semantic segmentation, object recognition and tracking. In many applications, complex systems, e.g., a robot equipped with visual sensors, learn state of surrounding environment via solving corresponding computer vision tasks. In turn, the solutions of these tasks can be helpful for making decisions about possible future actions. It is not surprising that their subsequent application in model-based predictive control should be taken into account when solving computer vision tasks. Reinforcement learning is one of modern machine learning technologies in which learning is carried out through interaction with the environment. In recent years, deep reinforcement learning has been used both for solving applied tasks like visual information analysis, and for solving specific computer vision problems, such as localizing objects in scenes.

In this PhD work, we will formalize the ideas of deep reinforcement learning in a tractable framework, and use it to develop a new type of inference models capable of several novel aspects of human-like learning, including learning 1) from the interaction with environment (no supervision information required), 2) efficiently and inference in real-time, 3) grounding concept representations in perceptions and action possibilities. The targeted applications include video analysis, robot vision and smart environment for assisted living.


We are seeking an enthusiastic individual to join the Data Science research group at WMG, University of Warwick with the following attributes:

• A minimum 2.1 undergraduate (BEng, MEng) and/or postgraduate masters’ qualification (MSc) in a science and technology field: Computer Science, Engineering, Mathematics, with specialisation in Computer Vision, Machine Learning and AI

• Familiarity with machine learning and probabilistic models

• Relevant software knowledge and experience, for example Python and tensor frameworks (PyTorch or TensorFlow), C++, etc

• Excellent analytical and numerical skills

• A driven, professional and independent work attitude

• Ability to liaise with academic supervisors from a range of disciplines

• Excellent written and verbal communication skills


The Data Science group, led by Prof. Giovanni Montana, actively develops machine learning algorithms to model and manage large volumes of data – including high-dimensional and unstructured (images, networks and texts) and time-evolving data ¬– to solve challenges for engineering, manufacturing and healthcare industry applications. In recent years, we have published extensively in prestigious AI & CV conferences, including ICML, CVPR, ACM MM, IJCAI and AAAI.


To apply please complete our online enquiry form and upload your CV. If you would like to be considered for this position or have any questions please complete our online enquiry form using the "Email Now" button below.

Please ensure you meet the minimum requirements before filling in the online form.

Funding Notes

Funding is available for UK/EU or (International applicants if she/he is willing to pay the difference of tuition fee) for 3 years.

Stipend Amount: Standard Research Council Maintenance Award - £15,009 for 3 years

This post is open to UK and EU nationals. International students may be considered if they are able to part-fund their studies at the difference in fees per year between home/UK and international fee rates.

For more information on course fees, please see here: View Website

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.