Translator Disclaimer
1 March 1992 Techniques for high-performance analog neural networks
Author Affiliations +
Abstract
We consider analog neural network implementations (using VLSI or optical technologies) with limited accuracy and various noise and nonlinearity error sources. Algorithms and techniques to achieve high performance (good recognition P'c% and large storage capacity) on such systems are considered. The adaptive clustering neural net (ACNN) and robust Ho-Kashyap (HK-2) associative processor (AP) are the neural networks considered in detail.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
David P. Casasent, Leonard Neiberg, and Sanjay S. Natarajan "Techniques for high-performance analog neural networks", Proc. SPIE 1608, Intelligent Robots and Computer Vision X: Neural, Biological, and 3-D Methods, (1 March 1992); https://doi.org/10.1117/12.135106
PROCEEDINGS
14 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Pattern recognition using stochastic neural networks
Proceedings of SPIE (August 19 1993)
Improved adaptive resonance theory
Proceedings of SPIE (January 31 1991)
Pattern recognition using Hilbert space
Proceedings of SPIE (October 31 1992)

Back to Top