Mathematics for Deep Learning
Combining theory, modelling, data, and computation to unlock the next generation of deep learning
Combining theory, modelling, data, and computation to unlock the next generation of deep learning
Machine learning, in particular Deep Learning (DL) based on ‘neural networks’, is one of the fastest growing areas of modern science and technology, which has potentially an enormous and transformative impact on all areas of our lives. The applications of DL embrace many disciplines such as biomedical sciences, computer vision, the physical sciences, the social sciences, speech recognition, gaming, music and finance.
However, alongside this explosive growth has been a concern about the lack of understanding behind DL and the way that DL based algorithms make their decisions. This leads to a lack of trustworthiness in the use of some of these algorithms. A reason for this is that the huge successes of Deep Learning are not all well understood, the results are sometimes mysterious, and there is often a lack of a clear link between the data training DL algorithms, and the decisions made by those algorithms. Maths4DL aims to put DL onto a firm mathematical grounding, and will combine theory, modelling, data and computation to help unlock the next generation of deep learning for important applications
The research work in the grant will comprise an interlocked set of work packages aimed to address both the theoretical development of DL (so that it becomes explainable) and the algorithmic development (so that it becomes trustworthy). These will then be linked to the development of DL in a number of key application areas, linked to and supported by industry, including medical image processing, partial differential equations and environmental problems.
The goals of Maths4DL will also contribute to international initiatives on Trustworthy AI focusing on the ethics of data, algorithms and practice within AI, as well as to wider initiatives on Explainable AI. We will engage with both of these communities to enhance the understanding of both these socially important questions.
If you would like to join the group and come along, please sign up to the reading group mailing list and we will let you know when the meetings are taking place.
The following topics will be discussed in the upcoming sessions:
|
Date |
Theme |
|
2/11/2023 |
Image processing |
|
16/11/2023 |
Image processing |
|
30/11/2023 |
Environmental data |
|
14/12/2023 |
Environmental data |
|
11/1/2024 |
Structure preserving deep learning |
|
25/1/2024 |
Structure preserving deep learning |
|
8/2/2024 |
Structure preserving deep learning |
