MSE Research Project Database

Deep interpretable neural networks


Project Leader: Saman Halgamuge
Collaborators: Chalini Wijetunga (Florey), Yahui Sun (ANU), Marnie Shaw (ANU)
Sponsors: ARC
Primary Contact: Saman Halgamuge (saman@unimelb.edu.au)
Keywords: artificial intelligence; data mining
Disciplines: Mechanical Engineering
Domains: Optimisation of resources and infrastructure

How do we approach problems like estimating the extent of climate change, using both collected evidence and existing knowledge or assumptions about the problem? The method of analysis to reach a conclusion should be transparent regardless of whether a panel of experts or a computer program is used. We need to be aware of the following questions too: Is the evidence we have an accurate account of the truth? Were they acquired correctly? Do they have missing pieces of important evidence?  We wish to have the perfect expert panel, which would scrutinise and use both the collected evidence and the existing knowledge or assumptions to reach a conclusion. PhD candidate is expected to have exceptional analytical skills and the completion of an undergraduate degree with a first class average in Engineering, Computer Sicence or Mathematics from a good quality university. 

Further information: https://scholar.google.com.au/citations?hl=en&user=9cafqywAAAAJ&view_op=list_works