25 October 1989 Projection Method Formulations Of Perceptron And Hopfield Associative Memory Neural Networks
Author Affiliations +
Proceedings Volume 1134, Optical Pattern Recognition II; (1989); doi: 10.1117/12.961610
Event: 1989 International Congress on Optical Science and Engineering, 1989, Paris, France
Abstract
Projection method formulations of the perceptron and Hopfield's associative content-addressable memory (ACAM) neural nets are presented. We show that the well-known single-layer perceptron learning algorithm can be formulated using the method of projections onto convex sets (POCS) and that its performance can be improved using this viewpoint. The operation of a modified, binary-valued Hopfield ACAM is shown to be equivalent to the method of generalized projections (GP). A direct extension of the binary-valued ACAM to the continuous-valued case lends itself to a POCS formu-lation.
© (1989) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
M. Ibrahim Sezan, Henry Stark, Shu-Jen Yeh, "Projection Method Formulations Of Perceptron And Hopfield Associative Memory Neural Networks", Proc. SPIE 1134, Optical Pattern Recognition II, (25 October 1989); doi: 10.1117/12.961610; https://doi.org/10.1117/12.961610
PROCEEDINGS
6 PAGES


SHARE
KEYWORDS
Binary data

Cesium

Content addressable memory

Neural networks

Optical pattern recognition

Detection and tracking algorithms

Signal processing

Back to Top