Energy-Efficient Multimedia Data Analysis with Tsetlin Machines

The urgent challenge of climate change demands innovative strategies to achieve Net Zero emissions. Multimedia data analysis, crucial for applications like environmental monitoring and smart cities, currently relies heavily on energy-intensive computer vision models. However, these significant energy consumption and associated carbon emissions are incompatible with Net Zero goals.

Tsetlin Machines (TMs) represent a form of interpretable machine learning that utilises propositional logic for decision making. Unlike traditional deep learning models, TMs operate with lower computational complexity and energy needs, making them ideal for sustainable AI applications to analyse multimodal data, including text, images, and sensor inputs, essential for comprehensive environmental analysis.

The candidate of this project will work closely with the Microsystems Group, Newcastle University. The candidate has a great opportunity to develop high-performance machine learning systems with low energy consumptions, which incorporate advanced techniques like self-supervised learning and model compression to achieve Net Zero objectives.

The objectives of this project are to use Tsetlin Machines to create AI models that demand less computational power and energy, addressing the high carbon footprint of traditional computer vision technologies. On top of this, TM-based systems can be further implemented to monitor and promote sustainability in sectors like agriculture, manufacturing, and urban planning through efficient multimodal data processing.

The core ambition of this PhD project is to set a new standard for AI applications, demonstrating that cutting-edge technology can be both powerful and environmentally friendly. By advancing Tsetlin Machine research and integrating it with self-supervised learning and model compression, this project aspires to produce AI systems that significantly reduce carbon footprints. The long-term vision and impact include deploying these systems across various industries, contributing to global efforts to achieve Net Zero emissions while maintaining high-performance standards.

Entry Requirements 

Essential Criteria:

• 2.1 or equivalent (or above) in Computer Science, or Electronics and Computer Engineering.
• Proficient coding skills and a good command of Python and machine learning frameworks such as Pytorch.
• Good knowledge of Microsystems.

Desirable Criteria:

• 1st class degree in Computer Science, or Electronics and Computer Engineering.
• Experience of Tsetlin Machine and embedded systems such as FPGA.
• Good track record of publications.

Newcastle University is committed to being a fully inclusive Global University which actively recruits, supports and retains colleagues from all sectors of society. We value diversity as well as celebrate, support and thrive on the contributions of all our employees and the communities they represent.  We are proud to be an equal opportunities employer and encourage applications from everybody, regardless of race, sex, ethnicity, religion, nationality, sexual orientation, age, disability, gender identity, marital status/civil partnership, pregnancy and maternity, as well as being open to flexible working practices.

Application enquires: 

Prof. Rishad Shafik, [email protected]

https://www.ncl.ac.uk/engineering/staff/profile/rishadshafik.html