John has (too) many research interests, but is currently focused on methods for unsupervised or semi-supervised (ideally one-shot) learning. In particular, he spends a lot of time thinking about representation learning, and generative models such as Generative Adversarial Networks, Variational Autoencoders and autoregressive neural models. He is also really into music, holds a Ph.D. in signal processing for musical audio from Maynooth University, and previously studied Computer Science at University College Cork and Music & Media Technologies at Trinity College Dublin.
