EvoWeb      
                         ContactsWhats newTourSearchSite map
The online information service for everyone interested in evolutionary computing
News & eventsCourses & careersResources & consultancyResourcesMembershipWorking groupsAdmin
  You are here:     Home page     Research & consultancy     EvoDebates: Fit for the future     Ian Parmee       

EvoDebates: Fit for the future - Ian Parmee

blank photo

Professor Ian Parmee, formerly Director of the Plymouth Engineering Design Centre, has recently joined the University of the West of England where he is currently establishing an Evolutionary Design and Decision Making research group. He is also the Director of Advanced Computational Technologies which specialises in the development and integration of evolutionary and adaptive search, exploration and optimisation strategies with complex industrial design and decision-making environments
http://www.ad-comtech.co.uk/
Membership record

In terms of my own research relating to design and decision-making, evolutionary computing techniques need to be seen as optimal information gatherers rather than optimisation tools. The major advantages of population-based search techniques, in my opinion, relate to their capability as powerful search and exploration algorithms that can provide diverse, interesting and potentially competitive solutions. Such solutions can provide information to the user which supports a better understanding of the problem domain and helps to define best directions for future investigation.

This capability is extremely important when operating within ill-defined and uncertain decision-making environments where initial fitness functions are largely conceptual and the initial task is to improve definition to increase confidence. Information gained from initial search utilising such models supports their development by the user in an iterative, interactive user/EC environment. In this sense the first task is to identify and model the problem domain before solving the problem.

Appropriate interaction is a key element and one that has received little attention. It is not necessary for the user to understand the detailed workings of the algorithms to interact and introduce online change to an evolutionary search and exploration process. Change here relates to the parameters and objectives that define the model rather than the many variables relating to the EC algorithm. EC variables require little tuning when search and exploration as opposed to optimisation is the main objective.

EC should not be seen as a stand-alone technology. In the development of highly interactive systems EC provides the underlying search capability and other technologies, some from the computational intelligence domain, provide the necessary control, information extraction, data-processing and presentation tasks. Overall systems could be considered "immersive" in that the user plays a central role receiving optimal/interesting information from the system and analysing such information offline before introducing change in terms of the underlying model/fitness function. In this manner it is possible that user knowledge of a particular problem area can be captured in further evolutionary search. It is also likely that the problem space from which the final solution is identified is significantly different from the initial space upon which the interactive search commenced.

Although the development of such systems is ambitious, the requirement for such design and decision-making support is universal. It is difficult to think of any technology other than EC that can provide the level of underlying search and exploration required across such ill-defined, uncertain problem spaces that most likely involve multiple objectives, constraint and high modality. Interaction can promote and achieve evolutionary search across a changing fitness landscape that eventually results in the identification of a competitive problem solution. Perhaps keywords relating to this form of EC utilisation are interactive search, exploration, discovery, innovation and creativity. In this sense EC can provide an excellent supporting role that enhances the decision-maker's knowledge and capabilities.


Comments

No comments have been submitted yet

DisclaimerPrivacy policy 03 Oct 2001 MirrorsMirrorsDeutschlandEspaņaFranceUK
EvoWeb is the website of EvoNet - EvoNet is funded by the European Commission's IST Programme
.