Project

Machine learning for meta-modelling in distributed computing environments

Code

05Y00308

Duration

01 March 2008 → 31 December 2012

Funding

Ghent University funding

Promotor

Tom Dhaene

Research disciplines

Natural sciences
- Applied mathematics in specific fields
- Artificial intelligence
- Computer architecture and networks
- Distributed computing
- Information sciences
- Information systems
- Programming languages
- Scientific computing
- Theoretical computer science
- Visual computing
- Other information and computing sciences
Social sciences
- Cognitive science and intelligent systems

Keywords

machine learning meta-models pro-active scheduling statistical modelling distibuted computing

Project description

During the design of complex systems (micro-electronics, MEMS, …) simplified 'meta-models' are often used to achieve tractability of analyses. These scalable meta-models are based on a limited number of detailed computer simulations. This project aims at developing new machine learning techniques for generating scalable meta-models in distributed computing environments (e.g. computer clusters and grids).