Maria has a BSc in Physics Engineering (IST, Portugal) and a PhD in Imaging Neuroscience from University College London, United Kingdom. After her PhD, she worked for five years has a researcher in Machine Learning for Neuroimaging at University College London and King’s College London. Her research focused on developing novel methods for diagnosing psychiatric disorders using MRI data and Machine Learning.
In the last five years before joining Anglia Ruskin University, Maria worked in industry as a customer-facing Deep Learning engineer at MathWorks. During these years she supported customers’ MATLAB workflows for Deep Learning applications and developed software for MATLAB’s Deep Learning Toolbox.
Her more recent interests focus on the application of Artificial Intelligence and Data Science to accelerate progress towards achieving the UN Sustainable Goals, particularly the Climate Change and Biodiversity goals.
Mihalik et al., Multiple holdouts with stability. Improving the generalizability of machine learning analyses of brain-behaviour relationships, Biological Psychiatry, 2020.
J. Rosa, et al., Sparse network-based models for patient classification using fMRI, NeuroImage, 2015.
J. Rosa, et al., PRoNTo: Pattern Recognition for Neuroimaging Toolbox, Neuroinformatics, 2013.
J. Rosa, et al., Bayesian comparison of local neurovascular coupling models using EEG-fMRI, PLoS Comp. Bio. 2011.
J. Rosa, et al., Bayesian model selection maps for group studies, NeuroImage, 2010.
J. Rosa, et al., Decoding the matrix: Benefits & limitations of applying machine learning to pain neuroimaging, Pain, 2014.
J. Rosa, Posterior Probability Maps, Brain Mapping: An Encyclopaedic Reference, Elsevier, 2015.
J. Rosa, Development & application of model selection methods for investigating brain function. PhD thesis, UCL, 2012.