Skip to main content

Staff Profile

Professor Jaume Bacardit

Professor of Artificial Intelligence

Background

I am a Professor of Artificial Intelligence at the School of Computing of Newcastle University since 2017. I am affiliated to the Interdisciplinary Computing and Complex BioSystems (ICOS) research group. My areas of expertise are artificial intelligence, bioinformatics and biomedical data analytics.


Research

My research interests include the development of machine learning methods for large-scale problems and their application to challenging problems, mostly involving biological data.


Academic background

I received a BEng and MEng in Computer Engineering and a PhD in Computer Science from the Ramon Llull University in Barcelona, Spain in 1998, 2000 and 2004, respectively.

My PhD thesis involved the adaptation and application of a class of rule-based machine learning methods called Learning Classifier Systems to Data Mining tasks in terms of scalability, knowledge representations and generalisation capacity.

From 2005 to 2007 I was a postdoc at the University of Nottingham working on Protein Structure Prediction. From 2008 to 2013 I was a Lecturer in Bioinformatics at the University of Nottingham, and from 2014 to 2017 i was Senior Lecturer in Biodata Mining at Newcastle University.


Google Scholar: Click here.

Research

My research interests include the development of machine learning methods for large-scale problems, the design of techniques to extract knowledge and improve the interpretability of machine learning algorithms, known as Explainable AI, and the application of machine learning to life sciences real-world problems.


I have led the data analytics efforts of several large biological/biomedical interdisciplinary consortiums: APPROACH (EU-IMI €15M, focusing on Osteoarthritis phenotype identification) and PORTABOLOMICS (£4.3M EPSRC Programme grant focusing on Engineering Biology).


My applied machine learning work at the interface with the life sciences has always been interdisciplinary, collaborating with data generators to make sense of their data, be it on plant science [1], animal behaviour [2,3,4], basic immunology [5,6,7], engineering biology [8,9] or Osteoarthritis [10,11,12,13].


Interpreting how machine learning models take decisions has been one of Bacardit’s active areas of research for many years, way before the term Explainable AI emerged. Most of his early work was done in the specific context of an application domains but these works motivated the generation of general-purpose methods for biological knowledge extraction of panels of biomarkers [14] or functional networks [15].


I have published papers on algorithmic advances to improve the scalability of machine learning methods [16], tackling challenges such as large dimensionality spaces [17], large sets of records [18], postprocessing operators [19] or using computational backends such as GPUs [20,21] or MapReduce [22,23].


I have 100+ peer-reviewed publications, 6900+ citations and an H-index of 39 (Google Scholar, as of March 2024).

Teaching
Publications