Statistical Machine Learning Program

[The SuperCom wiki is here:
http://buffet.rsise.anu.edu.au/cgi-bin/wiki.pl ]

Composite systems feature simple components organised into a highly reconfigurable and modular architecture, due to which they can appropriately assemble to achieve complex operations. A new generation of autonomous composite systems is being developed with the potential for important social, environmental and economic change. These include web and grid services, energy distribution systems, water management systems, chemical plant control systems, telecommunication and computer networks, to name but a few. The degree of autonomy -and ultimately the success- of this new generation systems will be largely determined by the existence of adequate supervision tools. These will need to confer the system the ability to self-diagnose and self-organise (assemble, reconfigure) to achieve optimal performance.

The scientific goal of the project is to develop theories, efficient (decentralised) algorithms and tools for the supervision of composite systems represented by discrete-event models, drawing on and adding to the fields of discrete-event systems, model-based diagnosis, AI planning, and symbolic model-checking. The practical goal of the project is to improve the quality of service in the web services, telecommunication, or water management industries, by transferring some of the technology developed to appropriate Australian partners.

Registration Date: Friday 07/01/2005 at 14:26 EST
Development Status: 0 - Undefined