Walter Hugo Lopez Pinaya
I am a Research Associate at the School of Biomedical Engineering & Imaging Science. I joined the AMIGO team to help translational research seeking to transform acute neurology through the application of novel, domain-tailored machine learning. My research focuses on developing deep learning models to learn the normative modelling of brain data. The main goal is to use these normative models to perform to improve triage and anomaly detection. Besides this, I have been working in developing the infrastructure to deploy processing pipelines to operate in Hospital-embedded HPC systems. This platform seeks to pioneer novel, state-of-the-art machine learning methods rendered uniquely feasible by the conjunction of high-performance computing with large-scale, comprehensive, fully-inclusive data, enabling large-scale distributed learning while assuring data security through the use of privacy-preserving generative models, and federated learning.
Projects
Neurology - StrokeRadiology - Triaging
Generative Modelling
Uncertainty Modelling