I'm a third-year PhD student in computer science at University College London. I am part of the Machine Reading group.
I'm working on extracting knowledge from matrix factorization models so one can understand why this complex model made a particular prediction. This knowledge is in the form of an interpretable model such as logic rules, decision trees and Bayesian networks.
My interests are Probabilistic Graphical Models, Machine Learning and Data Mining.
Talk (slides) at AAAI Spring Symposium 2015 in Stanford for the workshop paper Towards Extracting Faithful and Descriptive Representations of Latent Variable Models [pdf]
Short paper submitted at EMNLP 2015 on learning interpretable models from matrix factorization models