Development of genetic programming methods for rule extraction and knowledge representation
Brief: Concept design is a critical step in the process of design where multiple promising concepts are identified. Development of effective and efficient optimization methods to support concept design is a challenge as the number of variables representing a concept might vary from one to another while there could be some commonality in terms of several set of variables. The objective is to develop optimization methods that are capable of handling such classes of problems.
Skills Required: Good Matlab coding skills will be required. An understanding of optimization methods and in particular population based approaches such as Evolutionary Algorithms would be useful.
More details of the research activities at September 2014 34 http://seit.unsw.adfa.edu.au/research/sites/mdo/