Implementation of the morphological shared-weight neural network (MSNN) for target recognition on the Parallel Algebraic Logic (PAL) computer

Hongzheng Li; Hongchi Shi; Paul D. Gader; James M. Keller

doi:10.1117/12.323468

Translator Disclaimer

21 September 1998 Implementation of the morphological shared-weight neural network (MSNN) for target recognition on the Parallel Algebraic Logic (PAL) computer

Hongzheng Li, Hongchi Shi, Paul D. Gader, James M. Keller

Author Affiliations +

Proceedings Volume 3452, Parallel and Distributed Methods for Image Processing II; (1998) https://doi.org/10.1117/12.323468
Event: SPIE's International Symposium on Optical Science, Engineering, and Instrumentation, 1998, San Diego, CA, United States

Abstract

The morphological shared-weight neural network (MSNN) is an effective approach to automatic target recognition. Implementation of the network in parallel is critical for real-time target recognition systems. Although there is significant parallelism inherent in the MSNN, it is a challenge to implement it on an SIMD parallel computer consisting of a large array of simple processing elements. This paper discusses issues related to detection accuracy and throughput in implementing the MSNN on the Parallel Algebraic Logic computer.

Citation Download Citation

Hongzheng Li, Hongchi Shi, Paul D. Gader, and James M. Keller "Implementation of the morphological shared-weight neural network (MSNN) for target recognition on the Parallel Algebraic Logic (PAL) computer", Proc. SPIE 3452, Parallel and Distributed Methods for Image Processing II, (21 September 1998); https://doi.org/10.1117/12.323468

ACCESS THE FULL ARTICLE