1 November 1991 Failure of outer-product learning to perform higher-order mapping
Author Affiliations +
Abstract
Outer-product learning (also referred to as Hebbian learning) has been used as a very simple training algorithm for neural networks. Outer-product learning also has been proposed as a method for training a network with higher-order interconnections. It is shown in this paper that outer-product learning is inappropriate for higher-order networks because it does not have the ability to perform a non-monotonic mapping.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jason M. Kinser, Jason M. Kinser, } "Failure of outer-product learning to perform higher-order mapping", Proc. SPIE 1541, Infrared Sensors: Detectors, Electronics, and Signal Processing, (1 November 1991); doi: 10.1117/12.49333; https://doi.org/10.1117/12.49333
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Survey of neural networks as applied to target tracking
Proceedings of SPIE (June 22 1997)
Neural network target tracker
Proceedings of SPIE (July 31 1990)
Neural network transformation of arbitrary Boolean functions
Proceedings of SPIE (December 15 1992)
A Class of Continuous Level Neural Nets
Proceedings of SPIE (December 31 1986)
Neural network-based sensor signal accelerator
Proceedings of SPIE (February 01 2001)

Back to Top