Generative Adversarial Networks for Rare Event Augmentation

This project will produce synthetic data generation methods for creating synthetic data in data-limited situations, allowing the user to subsequently apply modern data intensive techniques, and hence make better decisions. Our main tool will be Generative Adversarial Networks (GANs), which are paired neural networks that we will train to simulate rare events.

GAN’s are a class of machine learning systems introduced by Goodfellow in 2014. The key idea is that two neural networks contest with each other in a game, in the sense of mathematical game theory, to improve each other’s performance. The Generative Network tries to synthesise new data that looks like it comes from the same source as our original data set, while the Discriminator Network tries to spot the fakes among the originals. As they compete, both networks improve, to the point where the generative network can synthesise new data indistinguishable from the old. An important feature of this approach is that neural networks can encode extremely complex dependencies in the data, and thus pick up features the user is unaware of.

This project has two main goals. The first is to develop a flexible Python library of GAN tools for data synthesis. This will be trialled and developed in collaboration with the data analytics team at DCWW. The second is to extend the application of GANs to rare event augmentation, though an intermediate parametric model, allowing a combination of supervised and unsupervised learning

HOW TO APPLY

Applicants should submit an application for postgraduate study via the online application service http://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/mathematics

In the research proposal section of your application, please specify the project title and supervisors of this project and copy the project description in the text box provided.

In the funding section, please select the ’self -funding’ option