Research themes

My research focuses on understanding deep learning from an empirical and scientific perspective, aiming to derive actionable insights that can improve its practical application. Major themes include:

:mag:   model interpretability via representation analysis

Deep learning works by transforming inputs into latent representations. Can we understand the information encoded in these representations?

:heavy_dollar_sign:   data-centric machine learning

Model behaviour depends critically on training data. Can we identify datapoints and subsets that influence key model properties?

:bar_chart:   model interpretability via feature attribution

How can we identify which input features a model relies on, and verify that attribution methods are faithful to model behaviour?

:muscle:   alternate notions of model robustness

Training adversarially robust models is expensive. Are there alternate robustness definitions that are both meaningful and easier to train for?

:recycle:   computational efficiency of deep models

How can we eliminate redundant neurons or weights in a pre-trained model while preserving performance?

Some other projects I have worked on: