In this year’s ICML, some interesting work was presented on Neural Processes. In this blog post, I discuss what Neural Processes are and how they behave as a prior over functions.
I am a Machine Learning researcher, passionate about creating novel AI/ML methods that would make a real impact towards advancing our understanding of biological sciences and improving human health. I am currently a Research Scientist at Novo Nordisk.
I did my PhD in Statistical Machine Learning at the University of Oxford, as part of the OxCSML group in the Department of Statistics, where I was supervised by Christopher Yau and Chris Holmes. Upon graduation, I had an opportunity to continue working with the Apple Health AI team, as well as spend some time in academia, in the Alan Turing Institute (as a recipient of the Turing-Crick Biomedical Data Science Award) and the Big Data Institute in Oxford.
I have a broad interest in developing generative models with a focus on tackling real-world biomedical problems.
My interests range from the intersection of Bayesian inference and deep learning (such as incorporating prior knowledge and structure within deep neural networks, multi-task/meta-learning etc) to research towards trustworthy ML for biomedical applications.
My PhD thesis focused on extensions of deep generative models, from Gaussian Process Latent Variable Models to Variational Autoencoders, with the goal to enable certain notions of feature-level interpretability for the analysis of high-dimensional tabular data.
R package implementing the Polya-Gamma augmentation scheme
Here you can find course material (in Estonian!) on Data Science and Visualisation, which we created together with Tanel Pärnamaa. This course “Statistiline andmeteadus ja visualiseerimine” is centered around a number of interesting case studies, and it focuses on teaching good practices of data science in R by applying statistical methods to solve these real-life problems.