I am currently a PhD student at University of Oxford, working to decipher the secret recipe of artificial intelligence.
Outside research, I teach, travel and hunt for good restaurants.
I also care very much about the environment and would love to promote diversity & equality in our society.
Shuyu Lin, Ronald Clark, Robert Birke, Niki Trigoni, Stephen Roberts
ArXiv preprint, 2019
Using a generative model with a latent variable that is shared by all data points can significantly improve the embedding accuracy, i.e. enhanced reconstruction quality in an auto-encoder or less information loss due to the embedding process.