I am currently a Professor of Data Science at the University of Warwick, with joint appointments in the Departments of Statistics and Warwick Manufacturing Group (WMG). My work focuses on developing and applying statistical and machine learning methods across diverse application domains.

After earning my PhD in computational statistics from the University of Warwick, I began my career as a postdoctoral researcher at the University of Chicago, where I developed statistical models for genetic variability in large populations and gene mapping. I then worked as a data scientist at Bristol-Myers Squibb in the USA, applying computational techniques to biomarker discovery.

In 2005, I joined Imperial College London as a Lecturer in the Mathematics Department and progressed to Reader (Associate Professor) by 2013. My research there focused on statistical machine learning methods, including building models to identify genetic variants linked to neuroimaging features of the human brain and addressing bioinformatics challenges involving omics data. In 2013, I joined King’s College London as Chair in Biostatistics and Bioinformatics, where I applied machine learning to medical imaging, particularly neuroimaging, and integrated multi-modal biomedical data to tackle healthcare challenges. I also began exploring deep learning methods for large-scale medical imaging applications during this time.

Since joining the University of Warwick in 2018, my research interests have expanded to include AI methods for sequential decision-making, particularly deep reinforcement learning and multi-agent systems. Supported by funding from EPSRC, MRC, CRUK, the Wellcome Trust, Innovate UK, and a UKRI Turing AI Acceleration Fellowship, my research aims to advance robust decision-making frameworks and leverage machine learning for impactful real-world applications. I have authored over 180 publications, contributing to methodological advances often motivated by applied challenges in areas such as neuroimaging and bioinformatics. Alongside my research, I have delivered courses ranging from introductory probability and statistics to PhD-level courses in pattern recognition and reinforcement learning.

I am a Chartered Statistician and Fellow of the Royal Statistical Society and have served on numerous grant review panels for funding bodies, including EPSRC, MRC, the Royal Society, and CRUK. My aim is to promote collaborative, interdisciplinary research that uses data science and machine learning to address important societal challenges.

Publications

Representative publications are listed below, and a full listing can be found on my Google Scholar profile.

Reinforcement learning and planning

• LeNSE: learning to navigate subgraph embeddings for large-scale combinatorial optimisation (with D. Ireland), ICML 2022
• Reinforcement learning for robotic manipulation using simulated locomotion demonstrations (with O. Kilinc), Machine Learning 2021
• Solving challenging dexterous manipulation tasks with trajectory optimisation and reinforcement learning (with H. Charlesworth), ICML 2021
• PlanGAN: model-based planning with sparse rewards and multiple goals (with H. Charlesworth), NeurIPS 2020
• Improving coordination in small-scale multi-agent deep reinforcement learning through memory-driven communication (with E. Pesce), Machine Learning 2020

Machine learning in computer vision

• Video object segmentation using point-based memory network (with M. Gao et al), Pattern Recognition 2022
• A persistent homology-based topological loss for CNN-based multi-class segmentation of CMR (with N. Byrne et al), IEEE Transactions in Medical Imaging 2022
• Automated triaging of adult chest radiographs with deep artificial neural networks (with M. Annarumma et al), Radiology 2019
• Learning to detect chest radiographs containing pulmonary lesions using visual attention networks (with E. Pesce et al), Medical Image Analysis 2019
• Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker (with J.H. Cole et al), NeuroImage 2017

Network data modelling

• Real‐time estimation of dynamic functional connectivity networks (with R. Pio Monti et. al.), Human Brain Mapping 2017
• Learning population and subject-specific brain connectivity networks via mixed neighborhood selection (with R. Pio Monti and C. Anagnostopoulos), Annals of Applied Statistics 2017
• Characterising brain network topologies: a dynamic analysis approach using heat kernels (with A.H. Chung et. al.), NeuroImage 2016
• Differential analysis of biological networks (with D. Ryan and A. Young), BMC Bioinformatics 2015
• Estimating time-varying brain connectivity networks from functional MRI time series (with R. Pio Monti et. al.), NeuroImage 2014

Regularised multivariate models

• Machine learning shows association between genetic variability in PPARG and cerebral connectivity in preterm infants (with M. Krishnan et. al.), PNAS 2017
• Sparse multi-view matrix factorization: a multivariate approach to multiple tissue comparisons (with Z. Wang and W. Yuan), Bioinformatics 2015
• The graph-guided group lasso for genome-wise association studies (with Z. Wang ), Regularisation, optimisation, kernels and support vector machines (book) 2014
• Network-guided regression for detecting associations between DNA methylation and gene expression (with Z. Wang and E. Curry), Bioinformatics 2014
• Discovering genetic associations with high-dimensional neuroimaging phenotypes: a sparse reduced-rank regression approach (with M. Vounou et. al.), NeuroImage 2010

Bayesian optimisation

• Identification of test cases for automated driving systems using Bayesian optimization (with B. Gangopadhyay et. al.), IEEE Intelligent Transportation Systems Conference 2019
• Dissociating frontoparietal brain networks with neuroadaptive Bayesian optimization (with R. Lorenz et al), Nature Communications 2018
• The automatic neuroscientist: a framework for optimizing experimental design with closed-loop real-time fMRI (with R. Lorenz et al), NeuroImage 2016
• Stopping criteria for boosting automatic experimental design using real-time fMRI with Bayesian optimization (with R. Lorenz et al), NIPS Workshop on Machine Learning and Interpretation in Neuroimaging 2015

Distance-based statistical models

• Random forest regression for manifold-valued responses (with D. Tsagkrasoulis), Pattern Recognition Letters 2018
• Distance‐based analysis of variance: approximate inference (with C. Minas), Statistical Analysis & Data Mining 2014
• Random forests on distance matrices for imaging genetics studies (with A. Sim and D. Tsagkrasoulis), Statistical Applications in Genetics & Molecular Biology 2013
• A distance-based test of association between paired heterogeneous genomic data (with C. Minas and E. Curry), Bioinformatics 2013
• Distance-based differential analysis of gene curves (with C. Minas and S.J. Widdell), Bioinformatics 2011

High-dimensional data clustering

• A Bayesian mixture of lasso regressions with t-errors (with A. Cozzini et. al.), Computational Statistics & Data Analysis 2014
• Subspace clustering of high-dimensional data: a predictive approach (with B. McWilliams), Data Mining & Knowledge Discovery 2014
• Model-based clustering with gene ranking using penalized mixtures of heavy-tailed distributions (with A. Cozzini and A. Jasra), Journal of Bioinformatics & Computational Biology 2013
• Multi‐view predictive partitioning in high dimensions (with B. McWilliams), Statistical Analysis & Data Mining 2012
• Predictive subspace clustering (with B. McWilliams), IEEE Conference on Machine Learning & Applications 2011

Functional data analysis

• A skew-t-normal multi-level reduced-rank functional PCA model for the analysis of replicated genomics time course data (with M. Berk), IDA 2012
• Longitudinal analysis of gene expression profiles using functional mixed-effects models (with M. Berk et. al.), Advanced Statistical Methods for the Analysis of Large Data Sets (book), 2012
• Functional modelling of microarray time series with covariate curves (with M. Berk), Statistica 2011
• A statistical framework for biomarker discovery in metabolomic time course data (with M. Berk and T. Ebbels), Bioinformatics 2011
• Modelling short time series in metabolomics: a functional data analysis approach (with M. Berk and T. Ebbels), Software Tools and Algorithms for Biological Systems (book), 2011

Streaming data modelling

• Adaptive regularization for lasso models in the context of nonstationary data streams (with R. Pio Monti and C. Anagnostopoulos), Statistical Analysis & Data Mining 2018
• Sparse partial least squares regression for on-line variable selection with multivariate data streams (with B. McWilliams), Statistical Analysis & Data Mining 2010
• Dynamic modelling of mean-reverting spreads for statistical arbitrage (with K. Triantafyllopoulos), Computational Management Science 2009
• Learning to trade with incremental support vector regression experts (with F. Parrella), International Workshop on Hybrid Artificial Intelligence Systems 2008
• Flexible least squares for temporal data mining and statistical arbitrage (with K. Triantafyllopoulos and T. Tsagaris), Experts Systems and Applications 2008

Selected media coverage

• AI as good as doctors at checking X-rays - study (BBC, 2023)
• World’s most advanced robotic hand is approaching human-level dexterity (Digital Trends, 2020)
• How AI could speed X-ray processing (BBC, 2019)
• See how this Artificial Intelligence can predict an abnormal chest X-ray (Forbes, 2019)
• This AI could hold the key to decoding human intelligence (Wired, 2017)
• The eyes don't have it: nose is most likely feature to be inherited (The Telegraph, 2017)
• Like mother, like daughter: face scanning technology reveals the features you're most likely to inherit from your parents (MailOnline, 2017)
• Deep-learning machine uses MRI scans to determine your brain age (MIT Technology Reviews, 2016)
• Predicting your brain age from MRI scans (NVIDIA Developer, 2016)

Contact details: g.montana@warwick.ac.uk
Data Science Research Group