Robustness of automatic target recognition using noniterative neural network

Chia-Lun John Hu

doi:10.1117/12.602593

Translator Disclaimer

19 May 2005 Robustness of automatic target recognition using noniterative neural network

Chia-Lun John Hu

Author Affiliations +

Proceedings Volume 5807, Automatic Target Recognition XV; (2005) https://doi.org/10.1117/12.602593
Event: Defense and Security, 2005, Orlando, Florida, United States

Abstract

When the M input training class patterns are represented by N-dimension analog vectors U_m, m=1 to M, the output P-bit binary classification vectors V_m, M=1 to M, of a one-layered, feed-forward neural network (OLNN) can be represented geometrically by P dichotomizing hyper-planes going through the origin of the N-dimension Euclidean coordinate in the N-space. In general, all these P planes divide the N-space into 2^P hyper-cones. Each cone contains one U_m and each cone corresponds to one V_m. Learning of the OLNN is then equivalent to establishing these P planes geometrically in the N-space such that, after the learning, if a test pattern vector T, not necessarily equal to any class pattern U_m, falls into the m-th cone (m=1 to 2^P) established by these P planes, this T will also be recognized as V_m. The robustness of this recognition is seen now to be equivalent to the geometrically allowed variation range of U_m in the m-th cone. This allowable range can be systematically adjusted for each cone during the learning process. This paper reports the optimum method of adjusting these variation ranges such that any unknown T containing environmental noise not included in the training can still be recognized with maximum accuracy.

Citation Download Citation

Chia-Lun John Hu "Robustness of automatic target recognition using noniterative neural network", Proc. SPIE 5807, Automatic Target Recognition XV, (19 May 2005); https://doi.org/10.1117/12.602593

ACCESS THE FULL ARTICLE