Strategies to efficiently train a neural network for an aerospace problem with a large multidimensional input space are developed and demonstrated. The neural network provides classification for over 100,000,000 data points. A query-based strategy is used that initiates training using a small input set, and then augments the set in multiple stages to include important data around the network decision boundary. Neural network inversion and oracle query are used to generate the additional data, jitter is added to the query data to improve the results, and an extended Kalman filter algorithm is used for training. A causality index is discussed as a means to reduce the dimensionality of the problem based on the relative importance of the inputs
D. C. Wunsch et al., "Efficient Training Techniques for Classification with Vast Input Space," Proceedings of the International Joint Conference on Neural Networks, 1999. IJCNN '99, Institute of Electrical and Electronics Engineers (IEEE), Jan 1999.
The definitive version is available at https://doi.org/10.1109/IJCNN.1999.831156
International Joint Conference on Neural Networks, 1999. IJCNN '99
Electrical and Computer Engineering
Keywords and Phrases
Kalman Filters; Aerospace Problem; Causality Index; Classification; Computational Complexity; Dimensionality Reduction; Efficient Training Techniques; Extended Kalman Filter Algorithm; Filtering Theory; Jitter; Learning (Artificial Intelligence); Multidimensional Input Space; Network Decision Boundary; Neural Nets; Neural Network; Neural Network Inversion; Oracle Query; Pattern Classification; Query-Based Strategy
Article - Conference proceedings
© 1999 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
01 Jan 1999