Optimizing Machine Learning for Embedded Systems
Research context:
The PhD opportunity focuses on optimizing machine learning for embedded systems.
While AI has shown success in solving complex tasks, there is a challenge in training deep learning models directly on embedded
devices due to computational complexity exceeding available resources. The project aims to address this challenge by
investigating existing learning approaches, developing new machine learning algorithms, and proposing optimization
techniques and hardware accelerators for on-device training, on-device continual learning, and on-device Bayesian learning.
Research goal:
The goal of this project is to develop novel and efficient learning systems that operate directly on embedded devices, enabling widespread access to the benefits of deep learning in practical and pervasive computing applications. Additionally, the project aims to reduce the carbon footprint associated with deep learning models by adopting low-power solutions. The advancements made through this research will guide the development of next-generation technologies and inspire further research in AI applications on embedded devices.
Candidate profile:
We are seeking highly motivated candidates with a strong background in computer science, machine learning, or a related field. The ideal candidate should possess solid programming skills, algorithm design expertise, and optimization techniques. While prior experience or knowledge in embedded systems and deep learning is advantageous, it is not mandatory. Strong analytical skills, problem-solving abilities, and excellent communication and collaboration skills are essential for success in this PhD position.
Further information:
This PhD position offers a supportive research environment, access to state-of-the-art facilities, and the opportunity to collaborate with leading researchers in the field. The successful candidate will receive a competitive stipend and opportunities for conference participation and publication of research findings.
Application details:
To apply for this position, interested candidates should submit a detailed CV, a cover letter outlining their research interests and motivation for pursuing a PhD in Optimizing Machine Learning for Embedded Systems, and provide contact information for two academic references. Shortlisted candidates will be invited for an interview to further discuss their research ideas and suitability for the position.
Expected start date: January, May, and September of each academic year.
Duration: This is a three-year position
For further information and application submission, please contact:
Primary supervisor: Dr. Shidrokh Goudarzi
Email: Shidrokh.goudarzi@uwl.ac.uk
Improving UAV Maneuvers and Control Using Distributed Sensor Arrays
Research context:
In recent years, UAV (Unmanned Aerial Vehicle) systems have undergone significant advancements, and it is anticipated that UAV-based services will generate markets valued at over £600 billion by 2050. These services encompass various applications, including the delivery of goods and medical supplies, as well as the inspection and maintenance of energy infrastructure. However, in order for UAV systems to realize their full potential, they must be capable of operating safely in complex environments where challenges such as sensing and predicting external disturbances, obstacle avoidance, and maneuvering in cluttered surroundings arise. Conventional controllers limit the operational capabilities of these aircraft. Therefore, the focus of this PhD research is to overcome this limitation by integrating distributed sensing and nonlinear flight control techniques.
Research goal:
The goal of this PhD research is to evaluate the effectiveness of different flight control strategies that utilize distributed sensing to enable agile UAV maneuvers. The research will explore three innovative technologies: bio-inspired distributed sensing, machine learning-based flight control, and wind tunnel dynamic testing. By applying machine learning techniques, the research aims to develop flight controllers that can effectively utilize the information obtained from distributed sensing arrays. Additionally, algorithms will be designed and simulated to model and analyze the performance of the proposed system. Real aerodynamic conditions will be used to test and evaluate the developed flight controllers.
Candidate profile:
We are seeking a highly motivated and qualified candidate with the following qualifications:
Further information:
The successful candidate will join a dynamic research team with access to state-of-the-art facilities and resources. The research project offers a unique opportunity to work on cutting-edge technologies in UAV control and maneuvering. The candidate will collaborate with experts in the field and have the chance to present research findings at international conferences and publish in reputable journals. Additionally, there may be opportunities for industrial collaborations and technology transfer.
Application details:
Interested candidates are invited to submit their applications, including the following documents:
Expected start date: January, May, and September of each academic year.
Duration: This is a three-year position
For further information and application submission, please contact:
Primary supervisor: Dr. Shidrokh Goudarzi
Email: Shidrokh.goudarzi@uwl.ac.uk
Smart City Big Data Processing with AI Algorithms
Research context:
As cities worldwide embrace the concept of smart cities, the generation of vast amounts of data presents an unprecedented opportunity to improve urban planning, resource management, and overall quality of life. However, effectively processing and extracting meaningful insights from this abundance of smart city data requires advanced AI algorithms. This PhD opportunity focuses on developing innovative approaches that leverage AI algorithms, particularly machine learning and deep learning models, for efficient and effective processing of big data in smart city environments. The aim is to enhance urban planning, resource allocation, and sustainability through intelligent systems and decision support tools.
Research goal:
The objective of this PhD research is to develop novel approaches that harness the power of AI algorithms, specifically machine learning and deep learning models, to process big data in smart city environments. The successful candidate will explore the application of these algorithms in various aspects of data processing, including data collection, integration, analysis, and visualization. Key research areas may include intelligent data analytics, predictive modeling, anomaly detection, and optimization techniques. The research outcomes will contribute to the advancement of smart cities by enabling more informed decision-making and improving resource allocation.
Candidate profile:
We are seeking a highly motivated and qualified candidate with the following qualifications:
Further information:
The successful candidate will join a dynamic research team with access to state-of-the-art facilities and resources. The research project offers a unique opportunity to work on cutting-edge technologies in UAV control and maneuvering. The candidate will collaborate with experts in the field and have the chance to present research findings at international conferences and publish in reputable journals. Additionally, there may be opportunities for industrial collaborations and technology transfer.
Application details:
Interested candidates are invited to submit their applications, including the following documents:
Expected start date: January, May, and September of each academic year.
Duration: This is a three-year position
For further information and application submission, please contact:
Primary supervisor: Dr. Shidrokh Goudarzi
Email: Shidrokh.goudarzi@uwl.ac.uk