Data Intensive Science in DISCnet

Our students will be trained to be highly numerate and computationally skilled, with access to a vast “toolkit” of methods, and experience in applying these methods to real research problems. In particular, we have expertise across the following areas of data intensive science:

  • Raw data processing
  • Image analysis
  • Pattern recognition,
  • Object detection
  • Object classification
  • Machine learning for classification and regression
  • Application of statistics to research problems
  • Multi-Variate Analyses
  • Bayesian methodologies for model parameter estimation
  • Hierarchical probabilistic modelling
  • Model selection
  • Numerical simulation on massive scales
  • Data mining
  • HPC (algorithms, software/system management, cloud applications)

Word cloud from the abstracts of the 77 PhD project proposals submitted to DISCnet