Query-based learning for aerospace applications

• Published in: IEEE transactions on neural networks Vol. 14; no. 6; pp. 1437 - 1448
• Main Authors: Saad, E.W., Choi, J.J., Vian, J.L., Wunsch, D.C.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-11-2003
• Subjects: Aerospace; Aerospace control; Aerospace industry; Aerospace safety; Aircraft components; Control systems; Dynamic range; Imaging phantoms; Industrial training; Inversions; Learning; Mathematical models; Networks; Neural networks; Supervised learning; Training; Training data
• ISSN: 1045-9227; 1941-0093
• DOI: 10.1109/TNN.2003.820826

Models of real-world applications often include a large number of parameters with a wide dynamic range, which contributes to the difficulties of neural network training. Creating the training data set for such applications becomes costly, if not impossible. In order to overcome the challenge, one can employ an active learning technique known as query-based learning (QBL) to add performance-critical data to the training set during the learning phase, thereby efficiently improving the overall learning/generalization. The performance-critical data can be obtained using an inverse mapping called network inversion (discrete network inversion and continuous network inversion) followed by oracle query. This paper investigates the use of both inversion techniques for QBL learning, and introduces an original heuristic to select the inversion target values for continuous network inversion method. Efficiency and generalization was further enhanced by employing node decoupled extended Kalman filter (NDEKF) training and a causality index (CI) as a means to reduce the input search dimensionality. The benefits of the overall QBL approach are experimentally demonstrated in two aerospace applications: a classification problem with large input space and a control distribution problem.