Hi, I'm Thomas! I'm a first year PhD student working on techniques to interpret deep neural networks from their weights.
Analyzing the weights of neural networks can provide general insights into what the model has learnt. This allows us to faithfully and generally study model behaviour without relying on specific inputs.
Machine learning models have become an undeniably useful tool in recent years. Yet, they remain shrouded in mystery; both in research and everyday use. Understanding these models will not only help their trustworthiness but guarantee their utility.
Outside of work, I love to go on long bike rides, game with friends, go skiing and wear shorts.