JPL Technical Report Server

Active learning for directed exploration of complex systems

Show simple item record Burl, Michael C. Wang, Esther 2014-08-07T21:38:43Z 2014-08-07T21:38:43Z 2009-06-14
dc.identifier.citation 26th International Conference on Machine Learning, Montreal, Canada, June 14-18, 2009 en_US
dc.identifier.clearanceno 09-1348
dc.description.abstract Physics-based simulation codes are widely used in science and engineering to model complex systems that would be infeasible to study otherwise. Such codes provide the highest-fidelity representation of system behavior, but are often so slow to run that insight into the system is limited. For example, conducting an exhaustive sweep over a d-dimensional input parameter space with k-steps along each dimension requires kᵈ simulation trials (translating into kᵈ CPU-days for one of our current simulations). An alternative is directed exploration in which the next simulation trials are cleverly chosen at each step. Given the results of previous trials, supervised learning techniques (SVM, KDE, GP) are applied to build up simplified predictive models of system behavior. These models are then used within an active learning framework to identify the most valuable trials to run next. Several active learning strategies are examined including a recently-proposed information-theoretic approach. Performance is evaluated on a set of thirteen synthetic oracles, which serve as surrogates for the more expensive simulations and enable the experiments to be replicated by other researchers. en_US
dc.description.sponsorship NASA/JPL en_US
dc.language.iso en_US en_US
dc.publisher Pasadena, CA : Jet Propulsion Laboratory, National Aeronautics and Space Administration, 2009 en_US
dc.subject simulations en_US
dc.subject information theory en_US
dc.subject kernel methods en_US
dc.subject oracles en_US
dc.title Active learning for directed exploration of complex systems en_US
dc.type Preprint en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record



My Account