Rasmus Hoegh

Rasmus is a PhD student at WSAudiology and the Technical University of Denmark (DTU). He is visiting ICSI through August, working in the space of neural differential equations in the Big Data group with Michael Mahoney. He is interested in probabilistic approaches to deep learning - especially deep generative models of sequential data and machine learning applied in health technology. Currently, he primarily researches how we can make audio models that generalize to real-world use scenarios. Specifically, he has been working on variational autoencoders and how probabilistic modelling enables us to e.g. learn robust latent representations, incorporate prior knowledge, and utilize uncertainty quantification. 

Website: http://rasmushoegh.com/