Dr Brian MacNamee

Lecturer/Assistant Professor

 email: brian.macnamee@ucd.ie
 Phone: +353 1 716 2315
 Room: E3.22

   Science East
   Belfield 
   Dublin 4

 Full Profile

I currently teach the following modules:

  • COMP40610 Computer Science: Information Visualisation
  • COMP10020 Computer Science: Introduction to Programming II
  • COMP47590 Computer Science: Advanced Machine Learning

 

My research focuses on machine learning, predictive analytics, and data visualisation. I am especially interested in the confluence of these different topics, and the opportunities they present for human-in-the-loop machine learning.

Selected publications:

  • "Fundamentals of machine learning for predictive data analytics: algorithms, worked examples, and case studies", JD Kelleher, B Mac Namee, A D'Arcy, MIT Press, 2015.
    www.machinelearningbook.com
  • "Agent Based Modeling in Computer Graphics and Games", B. Mac Namee, In: R.A.Meyers (eds).  Encyclopedia of Complexity and Systems Science. New York: Springer., pp. 604-621, 2012.
    https://link.springer.com/referenceworkentry/10.1007%2F978-1-4614-1800-9_39 
  • 'Stability of topic modeling via matrix factorization', Belford, Mark; Mac Namee, Brian; Greene, Derek, Expert Systems with Applications, 91 :159-169, 2018.
  • "Graphical perception of value distributions: an evaluation of non-expert viewers' data literacy", Arkaitz Zubiaga, Brian Mac Namee, The Journal of Community Informatics, 2016.
  • "A Taxonomy for Agent-Based Models in Human Infectious Disease Epidemiology", Elizabeth Hunter, Brian Mac Namee, John D. Kelleher, Jasss-The Journal Of Artificial Societies And Social Simulation, 20 (3), 2017.
  • "Robot perception errors and human resolution strategies in situated human-robot dialogue", Niels Schütte, Brian Mac Namee, John D. Kelleher, Advanced Robotics, 2017.
  • "Scoped: Visualising the Scope Chain Within Source Code" Bacher, I; Mac Namee, B; Kelleher, JD, In Proceedings of EuroVis 2017, 2017.
  • "Stacked-MLkNN: A stacking based improvement to Multi-Label k-Nearest Neighbours", Arjun Pakrashi and Brian Mac Namee, 1st International Workshop on Learning with Imbalanced Domains: Theory and Applications Co-located with ECML/PKDD 2017, 2017.
  • "The Code-Map Metaphor - A Review Of Its Use Within Software Visualisations", Bacher, I; Mac Namee, B; Kelleher, JD, In Proceedings of the International Conference on Information Visualization Theory and Applications, 2017.
  • "The problem of bias in training data in regression problems in medical decision support" MacNamee, B., Cunningham, P., Byrne, S., O.I. Corrigan, O.I., Artificial Intelligence in Medicine, 25 (1):51-70, 2002.

Full publication list available at: Google Scholar