| タイトル | Decision Manifold Approximation for Physics-Based Simulations |
| 本文（外部サイト） | http://hdl.handle.net/2060/20160003613 |
| 著者（英） | Samareh, Jamshid A.; Wong, Jay Ming |
| 発行日 | 2016-01-01 |
| 言語 | eng |
| 内容記述 | With the recent surge of success in big-data driven deep learning problems, many of these frameworks focus on the notion of architecture design and utilizing massive databases. However, in some scenarios massive sets of data may be difficult, and in some cases infeasible, to acquire. In this paper we discuss a trajectory-based framework that quickly learns the underlying decision manifold of binary simulation classifications while judiciously selecting exploratory target states to minimize the number of required simulations. Furthermore, we draw particular attention to the simulation prediction application idealized to the case where failures in simulations can be predicted and avoided, providing machine intelligence to novice analysts. We demonstrate this framework in various forms of simulations and discuss its efficacy. |
| NASA分類 | Cybernetics, Artificial Intelligence and Robotics |
| レポートNO | NF1676L-23423
NASA/TM-2016-219004
L-20657 |
| 権利 | Copyright, Distribution as joint owner in the copyright |
|
