My research is currently focused on developing principled methods for density estimation from incomplete data. My broader interests include deep density estimation, variational inference, deep learning, and software for machine learning.
I have obtained a MSc in Artificial Intelligence from the University of Edinburgh and a BEng in Software Engineering from the University of Southampton.
We propose an unsupervised representation learning method for a job title similarity model using noisy skill labels. We show that it is highly effective for tasks such as text ranking and job normalization.
We propose a new method for statistical model estimation from incomplete data, called variational Gibbs inference (VGI). Whilst being general-pupose, the proposed method outperforms existing VAE and normalising flow specific methods.