Machine Learning with Bio-Inspired Neural Networks
Primary supervisor
Contact admissions office
Other projects with the same supervisor
Funding
- Competition Funded Project (Students Worldwide)
This research project is one of a number of projects at this institution. It is in competition for funding with one or more of these projects. Usually the project which receives the best applicant will be awarded the funding. Applications for this project are welcome from suitably qualified candidates worldwide. Funding may only be available to a limited set of nationalities and you should read the full department and project details for further information.
Project description
This research will investigate machine learning using biologically inspired spiking neural networks. While much is known about how to train deep artificial neural networks, relatively little is understood about how the brain learns and processes information using electrical pulses known as 'spikes'. One feature of the brain that is well-understood, however, is its extremely low power consumption. Spiking neural networks are an evolution of the deep neural networks common in machine learning today, which promise to reduce drastically the energy footprint of AI systems, particularly when combined with neuromorphic hardware. This work will therefore explore bio-inspired AI algorithms suitable for this next-generation hardware.
The goal is to explore learning techniques observed in the brain, in combination with methods from the deep learning community, and their implementation in spiking neural network based AI algorithms. The research will target state-of-the-art solutions to traditional problems (e.g. image classification/segmentation and object detection, and natural language processing), and understanding of next-generation applications capable of exploiting neuromorphic principles. The work will research new paradigms such as online learning, developing new approaches to spatial and temporal credit assignment, and exploitation of principles from biology such as in-sensor and in-memory computing. Work will typically be simulation-based, making use of HPC/GPUs/neuromorphic hardware for modelling, and neural network description languages such as PyTorch, TensorFlow and other SNN modelling tools.
Please get in contact for more information and to discuss specific projects/applications.
Person specification
For information
- Candidates must hold a minimum of an upper Second Class UK Honours degree or international equivalent in a relevant science or engineering discipline.
- Candidates must meet the School's minimum English Language requirement.
- Candidates will be expected to comply with the University's policies and practices of equality, diversity and inclusion.
Essential
Applicants will be required to evidence the following skills and qualifications.
- You must be capable of performing at a very high level.
- You must have a self-driven interest in uncovering and solving unknown problems and be able to work hard and creatively without constant supervision.
Desirable
Applicants will be required to evidence the following skills and qualifications.
- You will have good time management.
- You will possess determination (which is often more important than qualifications) although you'll need a good amount of both.
General
Applicants will be required to address the following.
- Comment on your transcript/predicted degree marks, outlining both strong and weak points.
- Discuss your final year Undergraduate project work - and if appropriate your MSc project work.
- How well does your previous study prepare you for undertaking Postgraduate Research?
- Why do you believe you are suitable for doing Postgraduate Research?